Timezone: »
A central problem in learning from sequential data is representing cumulative history in an incremental fashion as more data is processed. We introduce a general framework (HiPPO) for the online compression of continuous signals and discrete time series by projection onto polynomial bases. Given a measure that specifies the importance of each time step in the past, HiPPO produces an optimal solution to a natural online function approximation problem. As special cases, our framework yields a short derivation of the recent Legendre Memory Unit (LMU) from first principles, and generalizes the ubiquitous gating mechanism of recurrent neural networks such as GRUs. This formal framework yields a new memory update mechanism (HiPPO-LegS) that scales through time to remember all history, avoiding priors on the timescale. HiPPO-LegS enjoys the theoretical benefits of timescale robustness, fast updates, and bounded gradients. By incorporating the memory dynamics into recurrent neural networks, HiPPO RNNs can empirically capture complex temporal dependencies. On the benchmark permuted MNIST dataset, HiPPO-LegS sets a new state-of-the-art accuracy of 98.3%. Finally, on a novel trajectory classification task testing robustness to out-of-distribution timescales and missing data, HiPPO-LegS outperforms RNN and neural ODE baselines by 25-40% accuracy.
Author Information
Albert Gu (Stanford)
Tri Dao (Stanford University)
Stefano Ermon (Stanford)
Atri Rudra (University at Buffalo, SUNY)
Chris Ré (Stanford)
Related Events (a corresponding poster, oral, or spotlight)
-
2020 Poster: HiPPO: Recurrent Memory with Optimal Polynomial Projections »
Wed Dec 9th 05:00 -- 07:00 PM Room Poster Session 3
More from the Same Authors
-
2020 Workshop: Differential Geometry meets Deep Learning (DiffGeo4DL) »
Joey Bose · Emile Mathieu · Charline Le Lan · Ines Chami · Frederic Sala · Christopher De Sa · Maximillian Nickel · Christopher Ré · Will Hamilton -
2020 Poster: Improved Techniques for Training Score-Based Generative Models »
Yang Song · Stefano Ermon -
2020 Poster: Probabilistic Circuits for Variational Inference in Discrete Graphical Models »
Andy Shih · Stefano Ermon -
2020 Poster: Efficient Learning of Generative Models via Finite-Difference Score Matching »
Tianyu Pang · Kun Xu · Chongxuan LI · Yang Song · Stefano Ermon · Jun Zhu -
2020 Poster: Belief Propagation Neural Networks »
Jonathan Kuck · Shuvam Chakraborty · Hao Tang · Rachel Luo · Jiaming Song · Ashish Sabharwal · Stefano Ermon -
2020 Oral: Hogwild!: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent »
Benjamin Recht · Christopher Ré · Stephen Wright · Feng Niu -
2020 Poster: Autoregressive Score Matching »
Chenlin Meng · Lantao Yu · Yang Song · Jiaming Song · Stefano Ermon -
2020 Poster: From Trees to Continuous Embeddings and Back: Hyperbolic Hierarchical Clustering »
Ines Chami · Albert Gu · Vaggos Chatziafratis · Christopher Ré -
2020 Poster: No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems »
Nimit Sohoni · Jared Dunnmon · Geoffrey Angus · Albert Gu · Christopher Ré -
2020 Poster: Diversity can be Transferred: Output Diversification for White- and Black-box Attacks »
Yusuke Tashiro · Yang Song · Stefano Ermon -
2020 Poster: MOPO: Model-based Offline Policy Optimization »
Tianhe Yu · Garrett Thomas · Lantao Yu · Stefano Ermon · James Zou · Sergey Levine · Chelsea Finn · Tengyu Ma -
2020 Poster: Multi-label Contrastive Predictive Coding »
Jiaming Song · Stefano Ermon -
2020 Oral: Multi-label Contrastive Predictive Coding »
Jiaming Song · Stefano Ermon -
2019 Workshop: KR2ML - Knowledge Representation and Reasoning Meets Machine Learning »
Veronika Thost · Christian Muise · Kartik Talamadupula · Sameer Singh · Christopher Ré -
2019 Workshop: Information Theory and Machine Learning »
Shengjia Zhao · Jiaming Song · Yanjun Han · Kristy Choi · Pratyusha Kalluri · Ben Poole · Alexandros Dimakis · Jiantao Jiao · Tsachy Weissman · Stefano Ermon -
2019 Poster: On the Downstream Performance of Compressed Word Embeddings »
Avner May · Jian Zhang · Tri Dao · Christopher Ré -
2019 Spotlight: On the Downstream Performance of Compressed Word Embeddings »
Avner May · Jian Zhang · Tri Dao · Christopher Ré -
2019 Poster: Multi-Resolution Weak Supervision for Sequential Data »
Paroma Varma · Frederic Sala · Shiori Sagawa · Jason Fries · Daniel Fu · Saelig Khattar · Ashwini Ramamoorthy · Ke Xiao · Kayvon Fatahalian · James Priest · Christopher Ré -
2019 Poster: Slice-based Learning: A Programming Model for Residual Learning in Critical Data Slices »
Vincent Chen · Sen Wu · Alexander Ratner · Jen Weng · Christopher Ré -
2019 Poster: Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulations. »
Sawyer Birnbaum · Volodymyr Kuleshov · Zayd Enam · Pang Wei Koh · Stefano Ermon -
2019 Poster: Hyperbolic Graph Convolutional Neural Networks »
Ines Chami · Zhitao Ying · Christopher Ré · Jure Leskovec -
2019 Poster: MintNet: Building Invertible Neural Networks with Masked Convolutions »
Yang Song · Chenlin Meng · Stefano Ermon -
2019 Poster: Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting »
Aditya Grover · Jiaming Song · Ashish Kapoor · Kenneth Tran · Alekh Agarwal · Eric Horvitz · Stefano Ermon -
2019 Poster: Meta-Inverse Reinforcement Learning with Probabilistic Context Variables »
Lantao Yu · Tianhe Yu · Chelsea Finn · Stefano Ermon -
2019 Poster: Approximating the Permanent by Sampling from Adaptive Partitions »
Jonathan Kuck · Tri Dao · Hamid Rezatofighi · Ashish Sabharwal · Stefano Ermon -
2019 Poster: Generative Modeling by Estimating Gradients of the Data Distribution »
Yang Song · Stefano Ermon -
2019 Oral: Generative Modeling by Estimating Gradients of the Data Distribution »
Yang Song · Stefano Ermon -
2018 Workshop: Relational Representation Learning »
Aditya Grover · Paroma Varma · Frederic Sala · Christopher Ré · Jennifer Neville · Stefano Ermon · Steven Holtzen -
2018 Poster: Streamlining Variational Inference for Constraint Satisfaction Problems »
Aditya Grover · Tudor Achim · Stefano Ermon -
2018 Poster: Semi-supervised Deep Kernel Learning: Regression with Unlabeled Data by Minimizing Predictive Variance »
Neal Jean · Sang Michael Xie · Stefano Ermon -
2018 Poster: Multi-Agent Generative Adversarial Imitation Learning »
Jiaming Song · Hongyu Ren · Dorsa Sadigh · Stefano Ermon -
2018 Poster: Constructing Unrestricted Adversarial Examples with Generative Models »
Yang Song · Rui Shu · Nate Kushman · Stefano Ermon -
2018 Poster: Bias and Generalization in Deep Generative Models: An Empirical Study »
Shengjia Zhao · Hongyu Ren · Arianna Yuan · Jiaming Song · Noah Goodman · Stefano Ermon -
2018 Spotlight: Bias and Generalization in Deep Generative Models: An Empirical Study »
Shengjia Zhao · Hongyu Ren · Arianna Yuan · Jiaming Song · Noah Goodman · Stefano Ermon -
2018 Poster: Amortized Inference Regularization »
Rui Shu · Hung Bui · Shengjia Zhao · Mykel J Kochenderfer · Stefano Ermon -
2018 Poster: Learning Compressed Transforms with Low Displacement Rank »
Anna Thomas · Albert Gu · Tri Dao · Atri Rudra · Christopher Ré -
2017 Workshop: Learning with Limited Labeled Data: Weak Supervision and Beyond »
Isabelle Augenstein · Stephen Bach · Eugene Belilovsky · Matthew Blaschko · Christoph Lampert · Edouard Oyallon · Emmanouil Antonios Platanios · Alexander Ratner · Christopher Ré -
2017 Workshop: ML Systems Workshop @ NIPS 2017 »
Aparna Lakshmiratan · Sarah Bird · Siddhartha Sen · Christopher Ré · Li Erran Li · Joseph Gonzalez · Daniel Crankshaw -
2017 Demonstration: Babble Labble: Learning from Natural Language Explanations »
Braden Hancock · Paroma Varma · Percy Liang · Christopher Ré · Stephanie Wang -
2017 Poster: Learning to Compose Domain-Specific Transformations for Data Augmentation »
Alexander Ratner · Henry Ehrenberg · Zeshan Hussain · Jared Dunnmon · Christopher Ré -
2017 Poster: A-NICE-MC: Adversarial Training for MCMC »
Jiaming Song · Shengjia Zhao · Stefano Ermon -
2017 Poster: Gaussian Quadrature for Kernel Features »
Tri Dao · Christopher M De Sa · Christopher Ré -
2017 Spotlight: Gaussian Quadrature for Kernel Features »
Tri Dao · Christopher M De Sa · Christopher Ré -
2017 Poster: Inferring Generative Model Structure with Static Analysis »
Paroma Varma · Bryan He · Payal Bajaj · Nishith Khandwala · Imon Banerjee · Daniel Rubin · Christopher Ré -
2017 Poster: InfoGAIL: Interpretable Imitation Learning from Visual Demonstrations »
Yunzhu Li · Jiaming Song · Stefano Ermon -
2017 Poster: Neural Variational Inference and Learning in Undirected Graphical Models »
Volodymyr Kuleshov · Stefano Ermon -
2016 Poster: Cyclades: Conflict-free Asynchronous Machine Learning »
Xinghao Pan · Maximilian Lam · Stephen Tu · Dimitris Papailiopoulos · Ce Zhang · Michael Jordan · Kannan Ramchandran · Christopher Ré · Benjamin Recht -
2016 Poster: Solving Marginal MAP Problems with NP Oracles and Parity Constraints »
Yexiang Xue · zhiyuan li · Stefano Ermon · Carla Gomes · Bart Selman -
2016 Poster: Generative Adversarial Imitation Learning »
Jonathan Ho · Stefano Ermon -
2016 Poster: Variational Bayes on Monte Carlo Steroids »
Aditya Grover · Stefano Ermon -
2016 Poster: Sub-sampled Newton Methods with Non-uniform Sampling »
Peng Xu · Jiyan Yang · Farbod Roosta-Khorasani · Christopher Ré · Michael W Mahoney -
2016 Poster: Adaptive Concentration Inequalities for Sequential Decision Problems »
Shengjia Zhao · Enze Zhou · Ashish Sabharwal · Stefano Ermon -
2015 Poster: Asynchronous stochastic convex optimization: the noise is in the noise and SGD don't care »
Sorathan Chaturapruek · John Duchi · Christopher Ré -
2015 Poster: Rapidly Mixing Gibbs Sampling for a Class of Factor Graphs Using Hierarchy Width »
Christopher M De Sa · Ce Zhang · Kunle Olukotun · Christopher Ré -
2015 Spotlight: Rapidly Mixing Gibbs Sampling for a Class of Factor Graphs Using Hierarchy Width »
Christopher M De Sa · Ce Zhang · Kunle Olukotun · Christopher Ré · Christopher Ré -
2015 Poster: Taming the Wild: A Unified Analysis of Hogwild-Style Algorithms »
Christopher M De Sa · Ce Zhang · Kunle Olukotun · Christopher Ré · Christopher Ré -
2014 Workshop: 4th Workshop on Automated Knowledge Base Construction (AKBC) »
Sameer Singh · Fabian M Suchanek · Sebastian Riedel · Partha Pratim Talukdar · Kevin P Murphy · Christopher Ré · William Cohen · Tom Mitchell · Andrew McCallum · Jason E Weston · Ramanathan Guha · Boyan Onyshkevych · Hoifung Poon · Oren Etzioni · Ari Kobren · Arvind Neelakantan · Peter Clark -
2014 Poster: Parallel Feature Selection Inspired by Group Testing »
Yingbo Zhou · Utkarsh Porwal · Ce Zhang · Hung Q Ngo · XuanLong Nguyen · Christopher Ré · Venu Govindaraju -
2013 Workshop: Big Learning : Advances in Algorithms and Data Management »
Xinghao Pan · Haijie Gu · Joseph Gonzalez · Sameer Singh · Yucheng Low · Joseph Hellerstein · Derek G Murray · Raghu Ramakrishnan · Michael Jordan · Christopher Ré -
2013 Poster: Embed and Project: Discrete Sampling with Universal Hashing »
Stefano Ermon · Carla Gomes · Ashish Sabharwal · Bart Selman -
2012 Poster: Density Propagation and Improved Bounds on the Partition Function »
Stefano Ermon · Carla Gomes · Ashish Sabharwal · Bart Selman -
2011 Poster: Accelerated Adaptive Markov Chain for Partition Function Computation »
Stefano Ermon · Carla Gomes · Ashish Sabharwal · Bart Selman -
2011 Spotlight: Accelerated Adaptive Markov Chain for Partition Function Computation »
Stefano Ermon · Carla Gomes · Ashish Sabharwal · Bart Selman