Skip to yearly menu bar Skip to main content


Poster

TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models

Yao Xiao ⋅ Qiqian Fu ⋅ Heyi Tao ⋅ Yuqun Wu ⋅ Zhen Zhu ⋅ Derek Hoiem
Dec 10, 2:00 AM - 5:00 AM Hall C1 #A723
Image-text models excel at image-level tasks but struggle with detailed visual understanding. While these models provide strong visual-language alignment, segmentation models like SAM2 offer precise spatial boundaries for objects. To this end, we propose TextRegion, a simple, effective, and training-free framework that combines the strengths of image-text models and SAM2 to generate powerful text-aligned region tokens. These tokens enable detailed visual understanding while preserving open-vocabulary capabilities. They can be directly applied to various downstream tasks, including open-world semantic segmentation, referring expression comprehension, and grounding. We conduct extensive evaluations and consistently achieve superior or competitive performance compared to state-of-the-art training-free methods. Additionally, our framework is compatible with many image-text models, making it highly practical and easily extensible as stronger models emerge. Code is available at: https://github.com/avaxiao/TextRegion.
Show more
View full details
Poster

DiPMInd: Distance profile based mutual independence testing for random objects

Yaqing Chen ⋅ Paromita Dubey
Dec 10, 2:00 AM - 5:00 AM Hall C1 #A106
This paper develops a novel unified framework for testing mutual independence among random objects residing in possibly different metric spaces. The framework generalizes existing methodologies and introduces new measures of mutual independence, and proposes associated tests that achieve minimax rate optimality and exhibit strong empirical power. The foundation of the proposed tests is the new concept of joint distance profiles, which uniquely characterize the joint law of random objects under a mild condition on either the joint law or the metric spaces. Our test statistics quantify the difference of the joint distance profiles of each data point with respect to the joint law and the product of marginal laws of the vector of random objects. To enhance power, we consider integrating this difference with respect to different measures and incorporate flexible data-adaptive weight profiles in the test statistics. We derive the limiting distribution of the test statistics under the null hypothesis of mutual independence and show that the proposed tests with certain weight profiles are asymptotically distribution-free if the marginal distance profiles are continuous. Furthermore, we establish the consistency of the tests under sequences of alternative hypotheses converging to the null. For practical implementations, we employ a permutation scheme to approximate the p-values and provide theoretical guarantees that the permutation-based tests maintain type I error control under the null and achieve consistency under alternatives. We demonstrate the power of the proposed tests across various types of data objects through simulations and real data applications, where the new tests exhibit better performance compared with popular existing approaches.
Show more
View full details
Poster

Continual Robot Learning via Language-Guided Skill Acquisition

Shuo Cheng ⋅ Zhaoyi Li ⋅ Kelin Yu ⋅ Danfei Xu
Dec 10, 8:30 AM - 11:30 AM Hall C1 #A828
To support daily human tasks, robots need to tackle complex, long-horizon tasks and continuously acquire new skills to handle new problems. Deep Reinforcement Learning (DRL) offers potential for learning fine-grained skills but relies heavily on human-defined rewards and faces challenges with long-horizon goals. Task and Motion Planning (TAMP) are adept at handling long-horizon tasks but often need tailored domain-specific skills, resulting in practical limitations and inefficiencies. To overcome these complementary limitations, we propose LG-SAIL (Language Models Guided Sequential, Adaptive, and Incremental Skill Learning), a framework that leverages Large Language Models (LLMs) to synergistically integrate TAMP and DRL for continuous skill learning in long-horizon tasks. Our framework achieves automatic task decomposition, operator creation, and dense reward generation for efficiently acquiring the desired skills. To facilitate new skill learning, our framework maintains a symbolic skill library and utilizes the existing model from semantic-related skills to warm start the training. LG-SAIL demonstrates superior performance compared to baselines across six challenging simulated task domains across two benchmarks. Furthermore, we demonstrate the ability to reuse learned skills to expedite learning in new task domains, and deploy the system on a physical robot platform. More results on website: https://sites.google.com/view/continuallearning.
Show more
View full details
Poster

Smooth Flow Matching for Synthesizing Functional Data

Jianbin Tan ⋅ Anru Zhang
Dec 10, 8:30 AM - 11:30 AM Hall C1 #A223
Functional data, i.e., random functions observed over a continuous domain, are increasingly available in areas such as biomedical research, health informatics, and epidemiology. However, effective statistical analysis for functional data is often hindered by challenges such as privacy constraints, sparse and irregular sampling, infinite-dimensionality, and non-Gaussian structures. To address these challenges, we introduce a novel framework named Smooth Flow Matching (SFM), tailored for generative modeling of functional data that enables statistical analysis without exposing sensitive real data. Under a copula framework, SFM constructs a semiparametric smooth flow to generate infinite-dimensional functional data, free of Gaussianity and low-rank assumptions. It is computationally efficient, handles irregular observations, and guarantees the smoothness of the generated functions, offering a practical and flexible solution in scenarios where existing deep generative methods are not applicable. Through extensive simulation studies, we demonstrate the advantages of SFM in terms of both synthetic data quality and computational efficiency. We then apply SFM to generate clinical trajectory data from the MIMIC-IV patient electronic health records (EHR) longitudinal database. Our analysis showcases the ability of SFM to produce high-quality surrogate data for downstream tasks, highlighting its potential to boost the utility of EHR data for clinical applications.
Show more
View full details
Poster

Rational Tuning of LLM Cascades via Probabilistic Modeling

Michael Zellinger ⋅ Matt Thomson
Dec 10, 8:30 AM - 11:30 AM Hall C1 #A107
Understanding the reliability of large language models (LLMs) has recently garnered significant attention. Given LLMs' propensity to hallucinate, as well as their high sensitivity to prompt design, it is already challenging to predict the performance of an individual LLM. However, the problem becomes more complex for compound LLM systems such as cascades, where in addition to each model's standalone performance, we must understand how the error rates of different models interact. In this paper, we present a probabilistic model for the joint performance distribution of a sequence of LLMs, which enables a framework for rationally tuning the confidence thresholds of a LLM cascade using continuous optimization. Compared to selecting confidence thresholds using Bayesian optimization, our parametric Markov-copula model yields more favorable error-cost trade-offs, improving the area under the error-cost curve by 4.3% on average for cascades with k ≥ 3 models. In the low-sample regime with n ≤ 30 training examples, the performance improvement widens to 10.2%, suggesting that our framework's inductive assumptions about the interactions between the error rates of different LLMs enhance sample efficiency. Overall, our Markov-copula model provides a rational basis for tuning LLM cascade performance and points to the potential of probabilistic methods in analyzing systems of LLMs.
Show more
View full details
Poster

Almost Sure Convergence of Linear Temporal Difference Learning with Arbitrary Features

Jiuqi Wang ⋅ Shangtong Zhang
Dec 10, 8:30 AM - 11:30 AM Hall C1 #A428
Temporal difference (TD) learning with linear function approximation (linear TD) is a classic and powerful prediction algorithm in reinforcement learning. While it is well-understood that linear TD converges almost surely to a unique point, this convergence traditionally requires the assumption that the features used by the approximator are linearly independent. However, this linear independence assumption does not hold in many practical scenarios. This work is the first to establish the almost sure convergence of linear TD without requiring linearly independent features. We prove that the weight iterates of linear TD converge to a bounded set, and that the value estimates derived from the weights in that set are the same almost everywhere. We also establish a notion of local stability of the weight iterates. Importantly, we do not impose assumptions tailored to feature dependence and do not modify the linear TD algorithm. Key to our analysis is a novel characterization of bounded invariant sets of the mean ODE of linear TD.
Show more
View full details
Poster

Generalized Robust Adaptive-Bandwidth Multi-View Manifold Learning in High Dimensions with Noise

Xiucai Ding ⋅ Chao Shen ⋅ Hau-Tieng Wu
Dec 11, 2:00 AM - 5:00 AM Hall C1 #A423
Multiview datasets are common in scientific and engineering applications, yet existing fusion methods offer limited theoretical guarantees, particularly in the presence of heterogeneous and high-dimensional noise. We propose Generalized Robust Adaptive-Bandwidth Multiview Diffusion Maps (GRAB-MDM), a new kernel-based diffusion geometry framework for integrating multiple noisy data sources. The key innovation of GRAB-MDM is a view-dependent bandwidth selection strategy that adapts to the geometry and noise level of each view, enabling a stable and principled construction of multiview diffusion operators. Under a common-manifold model, we establish asymptotic convergence results and show that the adaptive bandwidths lead to provably robust recovery of the shared intrinsic structure, even when noise levels and sensor dimensions differ across views. Numerical experiments demonstrate that GRAB-MDM significantly improves robustness and embedding quality compared with fixed-bandwidth and equal-bandwidth baselines, and usually outperform existing algorithms. The proposed framework offers a practical and theoretically grounded solution for multiview sensor fusion in high-dimensional noisy environments.
Show more
View full details
Poster

RPP: A Certified Poisoned-Sample Detection Framework for Backdoor Attacks under Dataset Imbalance

Miao Lin ⋅ Feng Yu ⋅ Rui Ning ⋅ Lusi Li ⋅ Jiawei Chen ⋅ Qian Lou ⋅ Mengxin Zheng ⋅ Chunsheng Xin ⋅ Hongyi Wu
Dec 11, 2:00 AM - 5:00 AM Hall C1 #A309
Deep neural networks are highly susceptible to backdoor attacks, yet most defense methods to date rely on balanced data, overlooking the pervasive class imbalance in real-world scenarios that can amplify backdoor threats. This paper presents the first in-depth investigation of how the dataset imbalance amplifies backdoor vulnerability, showing that (i) the imbalance induces a majority-class bias that increases susceptibility and (ii) conventional defenses degrade significantly as the imbalance grows. To address this, we propose Randomized Probability Perturbation (RPP), a certified poisoned-sample detection framework that operates in a black-box setting using only model output probabilities. For any inspected sample, RPP determines whether the input has been backdoor-manipulated, while offering provable within-domain detectability guarantees and a probabilistic upper bound on the false positive rate. Extensive experiments on five benchmarks (MNIST, SVHN, CIFAR-10, TinyImageNet and ImageNet10) covering 10 backdoor attacks and 12 baseline defenses show that RPP achieves significantly higher detection accuracy than state-of-the-art defenses, particularly under dataset imbalance. RPP establishes a theoretical and practical foundation for defending against backdoor attacks in real-world environments with imbalanced data.
Show more
View full details
Poster

Accelerating Inference of Discrete Autoregressive Normalizing Flows by Selective Jacobi Decoding

Jiaru Zhang ⋅ Juanwu Lu ⋅ Xiaoyu Wu ⋅ Ziran Wang ⋅ Ruqi Zhang
Dec 11, 2:00 AM - 5:00 AM Hall C1 #A609
Discrete normalizing flows are promising generative models with advantages such as analytical log-likelihood computation and end-to-end training. However, the architectural constraints to ensure invertibility and tractable Jacobian computation limit their expressive power and practical usability. Recent advancements utilize autoregressive modeling, significantly enhancing expressive power and generation quality. Nevertheless, such sequential modeling inherently restricts parallel computation during inference, leading to slow generation that impedes practical deployment. In this paper, we first identify that strict sequential dependency in inference is unnecessary to generate high-quality samples. We observe that sub-variables in sequential modeling can also be approximated without strictly conditioning on all preceding sub-variables. Moreover, the models tend to exhibit low dependency redundancy in the initial layer and higher redundancy in subsequent layers. Leveraging these observations, we propose to selectively use Jacobi decoding strategy that accelerates its autoregressive inference through parallel iterative optimization. Theoretical analyses demonstrate the method's superlinear convergence rate and guarantee that the number of iterations required is no greater than the original sequential approach. Empirical evaluations across multiple datasets validate the generality and effectiveness of our acceleration technique, achieving up to 4.7 times faster inference on modern normalizing flow models while preserving generation quality.
Show more
View full details
Poster

HDCS: Hierarchy Discovery and Critic Shaping for Reinforcement Learning with Automaton Specification

Duo XU ⋅ Faramarz Fekri
Dec 11, 2:00 AM - 5:00 AM Hall C1 #A1021
Training reinforcement learning (RL) agents by scalar reward signals is often infeasible when an environment has sparse and non-Markovian rewards. Deterministic finite-state automaton (DFA) provides a streamlined method for specifying tasks in reinforcement learning (RL) that surpass the limitations of traditional discounted return formulations. However, existing RL algorithms designed to address DFA tasks face unresolved challenges, hindering their practical application. One key issue is that subgoals in the DFA may exhibit hidden hierarchical structures, with some macro-subgoals comprising multiple micro-subgoals in certain orders. Without understanding this hierarchy, RL algorithms may struggle to efficiently solve tasks involving such macro-subgoals. Additionally, the sparse reward problem remains inadequately addressed. Previous approaches, such as potential-based reward shaping, often encounter inefficiencies or result in suboptimal solutions. To address these challenges, we propose a novel RL framework designed to uncover the hierarchical structure of subgoals and accelerating the solving of DFA tasks without changing the original optimal policies, short as HDCS. The framework operates in two phases: first, a hierarchical RL method is used to identify the prerequisites of subgoals and build the hierarchy; second, given any task specification (DFA), the subgoal hierarchy is incorporated into task DFA to make a product DFA, and then a simple and novel critic shaping approach is proposed to accelerate the satisfaction of product DFA, which does not change optimal policies of the original problem. The effectiveness of HDCS is demonstrated through experiments conducted across various domains. Especially, compared with representative baselines, the critic shaping can have 2X or 3X acceleration on task solving.
Show more
View full details
Poster

Understanding the Effects of Neuron Dominance in Deep Reinforcement Learning

Zifan Wu ⋅ Qian Lin ⋅ Blake Lawlor ⋅ Haijun Zhao ⋅ Daniel Brown
Dec 11, 8:30 AM - 11:30 AM Hall C1 #A512
Recent studies in deep reinforcement learning have revealed that neural networks tend to lose their capacity to adapt to new targets over the course of training. The proliferation of inactive neurons, i.e., the so-called ``dormant neurons'', has been identified as one source of capacity loss. This paper investigates \textit{dominant neurons}, neurons whose activation values are significantly larger than average, as a potential cause for neuron dormancy. We demonstrate the existence of dominant neurons in a number of visual control tasks, and perform an analysis of the learning dynamics showing how dominant neurons can induce dormancy in the subsequent layer. To gain a better understanding of this phenomenon, we examine it through the lens of representation learning and establish its connection with representation collapse. Furthermore, this paper evaluates several mitigation strategies for dominant neurons across a variety of visual control tasks. Our results show that strategies that induce lower peak activation scores tend to exhibit greater representational capacity, lower dormant neuron percentage, and better performance. Among these mitigation strategies, LayerNorm with weight decay has the strongest performance, despite its simplicity. Moreover, switching the value learning loss from regression to a classification loss also significantly mitigates the neuron dominance issue and improves the performance. As a potential explanation of the effectiveness of classification losses, we provide an analysis that shows how a classification loss can prevent representation collapse.
Show more
View full details
Poster

Generalized Smooth Stochastic Variational Inequalities: Almost Sure Convergence and Convergence Rates

Daniil Vankov ⋅ Angelia Nedich ⋅ Lalitha Sankar
Dec 11, 8:30 AM - 11:30 AM Hall C1 #A406
This paper focuses on solving a stochastic variational inequality (SVI) problem under relaxed smoothness assumption for a class of structured non-monotone operators. The SVI problem has attracted significant interest in the machine learning community due to its immediate application to adversarial training and multi-agent reinforcement learning. In many such applications, the resulting operators do not satisfy the smoothness assumption. To address this issue, we focus on a weaker generalized smoothness assumption called $\alpha$-symmetric. Under p-quasi sharpness and $\alpha$-symmetric assumptions on the operator, we study clipped projection (gradient descent-ascent) and clipped Korpelevich (extragradient) methods. For these clipped methods, we provide the first almost-sure convergence results without making any assumptions on the boundedness of either the stochastic operator or the stochastic samples. We also provide the first in-expectation unbiased convergence rate results for these methods under a relaxed smoothness assumption for $\alpha \leq 1/2$.
Show more
View full details
Poster

On the Convergence Analysis of Muon

Wei Shen ⋅ Ruichuan Huang ⋅ Minhui Huang ⋅ Cong Shen ⋅ Jiawei zhang
Dec 12, 2:00 AM - 5:00 AM Hall C1 #A308
The majority of parameters in neural networks are naturally represented as matrices. However, most commonly used optimizers treat these matrix parameters as flattened vectors during optimization, potentially overlooking their inherent structural properties. Recently, an optimizer called Muon has been proposed, specifically designed to optimize matrix-structured parameters. Extensive empirical evidence shows that Muon can significantly outperform traditional optimizers when training neural networks. Nonetheless, the theoretical understanding of Muon’s convergence behavior and the reasons behind its superior performance remain limited. In this work, we present a comprehensive convergence rate analysis of Muon and its comparison with Gradient Descent (GD). We characterize the conditions under which Muon can outperform GD. Our theoretical results reveal that Muon can benefit from the low-rank structure of Hessian matrices, a phenomenon widely observed in practical neural network training. Our experimental results support and corroborate the theoretical findings.
Show more
View full details
Poster

Align and Distill: Unifying and Improving Domain Adaptive Object Detection

Justin Kay ⋅ Timm Haucke ⋅ Suzanne Stathatos ⋅ Siqi Deng ⋅ Erik Young ⋅ Pietro Perona ⋅ Sara Beery ⋅ Grant Van Horn
Dec 12, 2:00 AM - 5:00 AM Hall C1 #A718
Object detectors often perform poorly on data that differs from their training set. Domain adaptive object detection (DAOD) methods have recently demonstrated strong results on addressing this challenge. Unfortunately, we identify systemic benchmarking pitfalls that call past results into question and hamper further progress: (a) Overestimation of performance due to underpowered baselines, (b) Inconsistent implementation practices preventing transparent comparisons of methods, and (c) Lack of generality due to outdated backbones and lack of diversity in benchmarks. We address these problems by introducing: (1) A unified benchmarking and implementation framework, Align and Distill (ALDI), enabling comparison of DAOD methods and supporting future development, (2) A fair and modern training and evaluation protocol for DAOD that addresses benchmarking pitfalls, (3) A new DAOD benchmark dataset, CFC-DAOD, increasing the diversity of available DAOD benchmarks, and (4) A new method, ALDI++, that achieves state-of-the-art results by a large margin. ALDI++ outperforms the previous state-of-the-art by +3.5 AP50 on Cityscapes to Foggy Cityscapes, +5.7 AP50 on Sim10k to Cityscapes (where ours is the only method to outperform a fair baseline), and +0.6 AP50 on CFC-DAOD. ALDI and ALDI++ are architecture-agnostic, setting a new state-of-the-art for YOLO and DETR-based DAOD as well without additional hyperparameter tuning. Our framework, dataset, and method offer a critical reset for DAOD and provide a strong foundation for future research.
Show more
View full details
Poster

Achieving adaptivity and optimality for multi-armed bandits using Exponential-Kullback Leibler Maillard Sampling

Hao Qin ⋅ Kwang-Sung Jun ⋅ Chicheng Zhang
Dec 12, 2:00 AM - 5:00 AM Hall C1 #A412
We study the problem of K-armed bandits with reward distributions belonging to a one-parameter exponential distribution family. In the literature, several criteria have been proposed to evaluate the performance of such algorithms, including Asymptotic Optimality, Minimax Optimality, Sub-UCB, and variance-adaptive worst-case regret bound. Thompson Sampling-based and Upper Confidence Bound-based algorithms have been employed to achieve some of these criteria. However, none of these algorithms simultaneously satisfy all the aforementioned criteria. In this paper, we design an algorithm, Exponential Kullback-Leibler Maillard Sampling (abbrev. Exp-KL-MS), that can achieve multiple optimality criteria simultaneously, including Asymptotic Optimality, Minimax Optimality with a \sqrt{ln(K)} factor, Sub-UCB, and variance-adaptive worst-case regret bound.
Show more
View full details
Poster

The Z-Gromov-Wasserstein Distance

Martin Bauer ⋅ Facundo Mémoli ⋅ Tom Needham ⋅ Mao Nishino
Dec 12, 2:00 AM - 5:00 AM Hall C1 #A529
The Gromov-Wasserstein (GW) distance is a powerful tool for comparing metric measure spaces which has found broad applications in data science and machine learning. Driven by the need to analyze data sets whose objects have increasingly complex structure (such as node and edge-attributed graphs), several variants of GW distance have been introduced in the recent literature. With a view toward establishing a general framework for the theory of GW-like distances, this paper considers a vast generalization of the notion of a metric measure space: for an arbitrary metric space Z, we define a Z-network to be a measure space endowed with a kernel valued in Z. We introduce a method for comparing Z-networks by defining a generalization of GW distance, which we refer to as Z-Gromov-Wasserstein (Z-GW) distance. This construction subsumes many previously known metrics and offers a unified approach to understanding their shared properties. This paper demonstrates that the Z-GW distance defines a metric on the space of Z-networks which retains desirable properties of Z, such as separability, completeness, and geodesicity. Many of these properties were unknown for existing variants of GW distance that fall under our framework. Our focus is on foundational theory, but our results also include computable lower bounds and approximations of the distance which will be useful for practical applications.
Show more
View full details
Poster

OpInf-LLM: Parametric PDE Solving with LLMs via Operator Inference

Zhuoyuan "Jacob" Wang ⋅ Hanjiang Hu ⋅ Xiyu Deng ⋅ Saviz Mowlavi ⋅ Yorie Nakahira
Dec 12, 2:00 AM - 5:00 AM Hall C1 #A815
Solving diverse partial differential equations (PDEs) is fundamental in science and engineering. Large language models (LLMs) have demonstrated strong capabilities in code generation, symbolic reasoning, and tool use, but reliably solving PDEs across heterogeneous settings remains challenging. Prior work on LLM-based code generation and transformer-based foundation models for PDE learning has shown promising advances. However, a persistent trade-off between execution success rate and numerical accuracy arises, particularly when generalization to unseen parameters and boundary conditions is required. In this work, we propose OpInf-LLM, an LLM parametric PDE solving framework via operator inference. The proposed framework leverages small amounts of solution data to enable accurate prediction of diverse PDE instances, including unseen parameters and configurations, and provides seamless integration with LLMs for natural language task specification and physics-based reasoning of proper feature parameterization. Its low computational demands and unified solution pipeline further enable a high execution success rate across heterogeneous settings, opening new possibilities for generalizable reduced-order modeling in LLM-based PDE solving.
Show more
View full details
Poster

Discovering Symbolic Differential Equations with Symmetry Invariants

Jianke Yang ⋅ Manu Bhat ⋅ Bryan Hu ⋅ Yadi Cao ⋅ Nima Dehmamy ⋅ Robin Walters ⋅ Rose Yu
Dec 12, 8:30 AM - 11:30 AM Hall C1 #A713
Discovering symbolic differential equations from data uncovers fundamental dynamical laws underlying complex systems. However, existing methods often struggle with the vast search space of equations and may produce equations that violate known physical laws. In this work, we address these problems by introducing the concept of symmetry invariants in equation discovery. We leverage the fact that differential equations admitting a symmetry group can be expressed in terms of differential invariants of symmetry transformations. Thus, we propose to use these invariants as atomic entities in equation discovery, ensuring the discovered equations satisfy the specified symmetry. Our approach integrates seamlessly with existing equation discovery methods such as sparse regression and genetic programming, improving their accuracy and efficiency. We validate the proposed method through applications to various physical systems, such as Darcy flow and reaction-diffusion, demonstrating its ability to recover parsimonious and interpretable equations that respect the laws of physics.
Show more
View full details
Poster

What Should Embeddings Embed? Autoregressive Models Represent Latent Generating Distributions

Liyi Zhang ⋅ Michael Li ⋅ R. Thomas McCoy ⋅ Ted Sumers ⋅ Jian-Qiao Zhu ⋅ Tom Griffiths
Dec 12, 8:30 AM - 11:30 AM Hall C1 #A307
Autoregressive language models have demonstrated a remarkable ability to extract latent structure from text. The embeddings from large language models have been shown to capture aspects of the syntax and semantics of language. But what should embeddings represent? We show that the embeddings from autoregressive models correspond to predictive sufficient statistics. By identifying settings where the predictive sufficient statistics are interpretable distributions over latent variables, including exchangeable models and latent state models, we show that embeddings of autoregressive models encode these explainable quantities of interest. We conduct empirical probing studies to extract information from transformers about latent generating distributions. Furthermore, we show that these embeddings generalize to out-of-distribution cases, do not exhibit token memorization, and that the information we identify is more easily recovered than other related measures. Next, we extend our analysis of exchangeable models to more realistic scenarios where the predictive sufficient statistic is difficult to identify by focusing on an interpretable subcomponent of language, topics. We show that large language models encode topic mixtures inferred by latent Dirichlet allocation (LDA) in both synthetic datasets and natural corpora.
Show more
View full details
Poster

Gradient descent inference in empirical risk minimization

Qiyang Han ⋅ Xiaocong Xu
Dec 12, 8:30 AM - 11:30 AM Hall C1 #A301
Gradient descent is one of the most widely used iterative algorithms in modern statistical learning. However, its precise algorithmic dynamics in high-dimensional settings remain only partially understood, which has limited its broader potential for statistical inference applications. This paper provides a precise, nonasymptotic joint distributional characterization of gradient descent iterates and their debiased statistics in a broad class of empirical risk minimization problems, in the so-called mean-field regime where the sample size is proportional to the signal dimension. Our nonasymptotic state evolution theory holds for both general nonconvex loss functions and non-Gaussian data, and reveals the central role of two Onsager correction matrices that precisely characterize the nontrivial dependence among all gradient descent iterates in the mean-field regime. Leveraging the joint state evolution characterization, we show that the gradient descent iterate retrieves approximate normality after a debiasing correction via a linear combination of observable loss derivative directions from all past iterates. Crucially, the debiasing coefficients are directly linked to the Onsager correction matrices, which can be estimated in a fully data-driven manner via the proposed gradient descent inference algorithm. This leads to a new algorithmic statistical inference framework based on debiased gradient descent, which (i) applies to a broad class of models with both convex and nonconvex losses, (ii) remains valid at each iteration without requiring algorithmic convergence and (iii) exhibits a certain robustness to possible model misspecification. As a by-product, our framework also provides algorithmic estimates of the generalization error at each iteration. We demonstrate our theory and inference methods in the canonical single-index regression model and a generalized logistic regression model, where the natural loss functions may exhibit arbitrarily nonconvex landscapes. Our analysis further shows that, in linear regression with squared loss, the proposed debiased gradient descent iterate eventually coincides with the debiased convex regularized estimator in a mean-field distributional sense, and the quality of statistical inference for the unknown signal aligns exactly with the generalization error achieved along the algorithmic trajectory.
Show more
View full details
Poster

Paradoxical noise preference in RNNs

Noah Eckstein ⋅ Manoj Srinivasan
Dec 12, 8:30 AM - 11:30 AM Hall C1 #A720
In recurrent neural networks (RNNs) used to model biological neural networks, noise is typically introduced during training to emulate biological variability and regularize learning. The expectation is that removing the noise at test time should preserve or improve performance. Contrary to this intuition, we find that continuous-time recurrent neural networks (CTRNNs) often perform best at a nonzero noise level, often approximately the same level used during training. This noise preference typically arises when noise is injected inside the neural activation function; networks trained with noise injected outside the activation function perform best with zero noise. The phenomenon arises robustly in diverse tasks for large enough training noise including function approximation, maze navigation, 2D path integration, and a multi-task suite from cognitive neuroscience; we also show the phenomenon arising in feedforward neural networks, not just in RNNs. Through analyses of simple function-approximation and single-neuron regulator tasks, we show that the phenomenon stems from noise-induced shifts of fixed points (stationary distributions) in the underlying stochastic dynamics of the RNNs, thereby providing some mechanistic interpretability of the phenomenon. These fixed point shifts are noise-level dependent and bias the network outputs when the noise is removed, degrading performance. Analytical and numerical results show that the bias arises when neural states operate near activation-function nonlinearities, where noise is asymmetrically attenuated, and that performance optimization incentivizes operation near these nonlinearities; such performance incentives exist for networks with noise inside the activation function, but not for networks with noise outside the activation function, explaining why only noise-in networks show preference. Thus, networks can overfit to the stochastic training environment itself rather than just to the input–output data. The phenomenon is distinct from stochastic resonance, wherein nonzero noise enhances signal processing. Our findings reveal that training noise can become an integral part of the computation learned by recurrent networks, with implications for understanding neural population dynamics and for the design of robust artificial RNNs.
Show more
View full details
Poster

FedIndex: Federated Domain Adaptation with Continuous Domain Indices

qingyang yu ⋅ Hao Wang ⋅ Qizhen Zhang ⋅ Hao Wang
Dec 12, 8:30 AM - 11:30 AM Hall C1 #A106
Federated domain adaptation incorporates source clients’ knowledge to improve the model performance on the target client under the coordination of the server, mitigating the im- pact of data insufficiency and domain shift. Existing federated domain adaptation (FDA) methods focus on domain adaptation with categorical domain indices (e.g., “source” and “target”), while many real-world tasks involve domains with continuous domain indices. For instance, hospitals need to adapt disease analysis and prediction across patients via age, a continuous domain index in medical applications capturing the underlying relation between patient information and disease analysis. Prior FDA methods struggle with such tasks due to their ignorance of continuous domain indices. This paper proposes FedIndex to enable FDA with continuous domain indices. FedIndex performs adversarial domain adaptation across clients with the help of a global discriminator, aligning all domains’ distributions. Our theoretical analysis demonstrates the capability of FedIndex to generate domain-invariant features across clients using continuous domain indices without accessing data on clients, simultaneously maintaining privacy preservation. Our empirical results show that FedIndex outperforms the state-of-the-art FDA methods on synthetic and real-world datasets.
Show more
View full details
Poster

A Multi-Fidelity Control Variate Approach for Policy Gradient Estimation

Xinjie Liu ⋅ Cyrus Neary ⋅ Kushagra Gupta ⋅ Wesley Suttle ⋅ Christian Ellis ⋅ Ufuk Topcu ⋅ David Fridovich-Keil
Dec 12, 8:30 AM - 11:30 AM Hall C1 #A529
Many reinforcement learning (RL) algorithms are impractical for deployment in operational systems or for training with computationally expensive high-fidelity simulations, as they require large amounts of data. Meanwhile, low-fidelity simulators—such as reduced-order models, heuristic reward functions, or generative world models—can cheaply provide useful data for RL training, even if they are too coarse for direct sim-to-real transfer. We propose multi-fidelity policy gradients (MFPGs), an RL framework that mixes a small amount of data from the target environment with a control variate formed from a large volume of low-fidelity simulation data to construct an unbiased, variance-reduced estimator for on-policy policy gradients. We instantiate the framework by developing a practical, multi-fidelity variant of the classical REINFORCE algorithm. We show that under standard assumptions, the MFPG estimator guarantees asymptotic convergence of multi-fidelity REINFORCE to locally optimal policies in the target environment, and achieves faster finite-sample convergence rates compared to training with high-fidelity data alone. We evaluate the MFPG algorithm across a suite of simulated robotics benchmark tasks in scenarios with limited high-fidelity data but abundant off-dynamics, low-fidelity data. In our baseline comparisons, for scenarios where low-fidelity data are neutral or beneficial and dynamics gaps are mild to moderate, MFPG is, among the evaluated off-dynamics RL and low-fidelity-only approaches,the only method that consistently achieves statistically significant improvements in mean performance over a baseline trained solely on high-fidelity data. When low-fidelity data become harmful, MFPG exhibits the strongest robustness against performance degradation among the evaluated methods, whereas strong off-dynamics RL methods tend to exploit low-fidelity data aggressively and fail substantially more severely. An additional experiment in which the high- and low-fidelity environments are assigned anti-correlated rewards shows that MFPG can remain effective even when the low-fidelity environment exhibits reward misspecification. Thus, MFPG not only offers a reliable and robust paradigm for exploiting low-fidelity data, e.g., to enable efficient sim-to-real transfer, but also provides a principled approach to managing the trade-off between policy performance and data collection costs.
Show more
View full details