Workshop
The Symbiosis of Deep Learning and Differential Equations -- III
Luca Herranz-Celotti 路 Martin Magill 路 Ermal Rrapaj 路 Winnie Xu 路 Qiyao Wei 路 Archis Joglekar 路 Michael Poli 路 Animashree Anandkumar
Room 255 - 257
Sat 16 Dec, 6:30 a.m. PST
In the deep learning community, a remarkable trend is emerging, where powerful architectures are created by leveraging classical mathematical modeling tools from diverse fields like differential equations, signal processing, and dynamical systems. Differential equations are a prime example: research on neural differential equations has expanded to include a large zoo of related models with applications ranging from time series analysis to robotics control. Score-based diffusion models are among state-of-the-art tools for generative modelling, drawing connections between diffusion models and neural differential equations. Other examples of deep architectures with important ties to classical fields of mathematical modelling include normalizing flows, graph neural diffusion models, Fourier neural operators, architectures exhibiting domain-specific equivariances, and latent dynamical models (e.g., latent NDEs, H3, S4, Hyena). The previous two editions of the Workshop on the Symbiosis of Deep Learning and Differential Equations have promoted the bidirectional exchange of ideas at the intersection of classical mathematical modelling and modern deep learning. On the one hand, this includes the use of differential equations and similar tools to create neural architectures, accelerate deep learning optimization problems, or study theoretical problems in deep learning. On the other hand, the Workshop also explores the use of deep learning methods to improve the speed, flexibility, or realism of computer simulations. Last year, we noted a particularly keen interest from the audience in neural architectures that leveraged classical mathematical models, such as those listed above. We therefore propose that the third edition of this Workshop focus on this theme.
Schedule
Sat 6:30 a.m. - 6:45 a.m.
|
Introduction and opening remarks
(
Introduction
)
>
SlidesLive Video |
馃敆 |
Sat 6:45 a.m. - 7:30 a.m.
|
Philip M. Kim - Machine learning methods for protein, peptide and antibody design.
(
Keynote Talk
)
>
SlidesLive Video |
馃敆 |
Sat 7:30 a.m. - 7:45 a.m.
|
Effective Latent Differential Equation Models via Attention and Multiple Shooting
(
Spotlight
)
>
link
SlidesLive Video |
Germ谩n Abrevaya 路 Mahta Ramezanian-Panahi 路 Jean-Christophe Gagnon-Audet 路 Pablo Polosecki 路 Irina Rish 路 Silvina Ponce Dawson 路 Guillermo Cecchi 路 Guillaume Dumas 馃敆 |
Sat 7:45 a.m. - 8:00 a.m.
|
Adaptive Resolution Residual Networks
(
Spotlight
)
>
link
SlidesLive Video |
L茅a Demeule 路 Mahtab Sandhu 路 Glen Berseth 馃敆 |
Sat 8:00 a.m. - 8:15 a.m.
|
Break
|
馃敆 |
Sat 8:15 a.m. - 9:00 a.m.
|
Poster Session 1
(
Poster Session
)
>
|
馃敆 |
Sat 9:00 a.m. - 9:45 a.m.
|
Yulia Rubanova - Learning efficient and scalable simulation using graph networks.
(
Keynote Talk
)
>
SlidesLive Video |
馃敆 |
Sat 9:45 a.m. - 10:00 a.m.
|
Can Physics informed Neural Operators self improve?
(
Spotlight
)
>
link
SlidesLive Video |
Ritam Majumdar 路 Amey Varhade 路 Shirish Karande 路 Lovekesh Vig 馃敆 |
Sat 10:00 a.m. - 11:00 a.m.
|
Lunch Break
(
Lunch Break
)
>
|
馃敆 |
Sat 11:00 a.m. - 11:45 a.m.
|
Michael Bronstein - Physics-inspired learning on graphs.
(
Keynote Talk
)
>
SlidesLive Video |
馃敆 |
Sat 11:45 a.m. - 12:00 p.m.
|
Vertical AI-driven Scientific Discovery
(
Spotlight
)
>
link
SlidesLive Video |
Yexiang Xue 馃敆 |
Sat 12:00 p.m. - 12:15 p.m.
|
ELeGANt: An Euler-Lagrange Analysis of Wasserstein Generative Adversarial Networks
(
Spotlight
)
>
link
SlidesLive Video |
Siddarth Asokan 路 Chandra Seelamantula 馃敆 |
Sat 12:15 p.m. - 1:00 p.m.
|
Albert Gu - Structured State Space Models for Deep Sequence Modeling.
(
Keynote Talk
)
>
SlidesLive Video |
馃敆 |
Sat 1:00 p.m. - 1:15 p.m.
|
TANGO: Time-reversal Latent GraphODE for Multi-Agent Dynamical Systems
(
Spotlight
)
>
link
SlidesLive Video |
Zijie Huang 路 Wanjia Zhao 路 Jingdong Gao 路 Ziniu Hu 路 Xiao Luo 路 Yadi Cao 路 Yuanzhou Chen 路 Yizhou Sun 路 Wei Wang 馃敆 |
Sat 1:15 p.m. - 1:30 p.m.
|
Break
|
馃敆 |
Sat 1:30 p.m. - 2:30 p.m.
|
Poster Session 2
(
Poster Session
)
>
|
馃敆 |
Sat 2:30 p.m. - 2:45 p.m.
|
Closing Remarks
(
Closing Remarks
)
>
SlidesLive Video |
馃敆 |
-
|
Physics-Informed Transformer Networks ( Poster ) > link | Fabricio Dos Santos 路 Tara Akhound-Sadegh 路 Siamak Ravanbakhsh 馃敆 |
-
|
Generalized One-Shot Transfer Learning of Linear Ordinary and Partial Differential Equations ( Poster ) > link | Pavlos Protopapas 路 Hari Raval 馃敆 |
-
|
Towards Optimal Network Depths: Control-Inspired Acceleration of Training and Inference in Neural ODEs ( Poster ) > link | Keyan Miao 路 Konstantinos Gatsis 馃敆 |
-
|
Causal Graph ODE: Continuous Treatment Effect Modeling in Multi-agent Dynamical Systems ( Poster ) > link | Zijie Huang 路 Jeehyun Hwang 路 Junkai Zhang 路 Jinwoo Baik 路 Weitong ZHANG 路 Quanquan Gu 路 Dominik Wodarz 路 Yizhou Sun 路 Wei Wang 馃敆 |
-
|
Data-Driven Neural-ODE Modeling for Breast Cancer Tumor Dynamics and Progression-Free Survival Predictions ( Poster ) > link | Jinlin Xiang 路 Bozhao Qi 路 Qi Tang 路 Marc Cerou 路 Wei Zhao 馃敆 |
-
|
Orthogonal Polynomials Quadrature Algorithm: a functional analytic approach to inverse problems in deep learning ( Poster ) > link | Lilian Wong 馃敆 |
-
|
Advancing Graph Neural Networks Through Joint Time-Space Dynamics ( Poster ) > link | Qiyu Kang 路 Yanan Zhao 路 Kai Zhao 路 Xuhao Li 路 Qinxu Ding 路 Wee Peng Tay 路 Sijie Wang 馃敆 |
-
|
Two-Step Bayesian PINNs for Uncertainty Estimation ( Poster ) > link | Pablo Flores 路 Olga Graf 路 Pavlos Protopapas 路 Karim Pichara 馃敆 |
-
|
Solvers are also Wayfinders: Neural ODEs for Multi-Agent Pathplanning ( Poster ) > link | Progyan Das 路 Dwip Dalal 馃敆 |
-
|
Physics-Informed Neural Operators with Exact Differentiation on Arbitrary Geometries ( Poster ) > link | Colin White 路 Julius Berner 路 Jean Kossaifi 路 Mogab Elleithy 路 David Pitt 路 Daniel Leibovici 路 Zongyi Li 路 Kamyar Azizzadenesheli 路 Animashree Anandkumar 馃敆 |
-
|
PINNs-Torch: Enhancing Speed and Usability of Physics-Informed Neural Networks with PyTorch ( Poster ) > link | Reza Akbarian Bafghi 路 Maziar Raissi 馃敆 |
-
|
One-Shot Transfer Learning for Nonlinear ODEs ( Poster ) > link | Wanzhou Lei 路 Pavlos Protopapas 路 Joy Parikh 馃敆 |
-
|
Deep PDE Solvers for Subgrid Modelling and Out-of-Distribution Generalization ( Poster ) > link | Patrick Chatain 路 Adam Oberman 馃敆 |
-
|
Multiscale Neural Operators for Solving Time-Independent PDEs ( Poster ) > link | Winfried Ripken 路 Lisa Coiffard 路 Felix Pieper 路 Sebastian Dziadzio 馃敆 |
-
|
Individualized Dosing Dynamics via Neural Eigen Decomposition ( Poster ) > link | Stav Belogolovsky 路 Ido Greenberg 路 Danny Eytan 路 Shie Mannor 馃敆 |
-
|
Neural Differential Recurrent Neural Network with Adaptive Time Steps ( Poster ) > link | Yixuan Tan 路 Liyan Xie 路 Xiuyuan Cheng 馃敆 |
-
|
Evaluating Uncertainty Quantification approaches for Neural PDEs in scientific application ( Poster ) > link | Vardhan Dongre 路 Gurpreet Singh Hora 馃敆 |
-
|
Multimodal base distributions for continuous-time normalising flows ( Poster ) > link | Shane Josias 路 Willie Brink 馃敆 |
-
|
Unifying Neural Controlled Differential Equations and Neural Flow for Irregular Time Series Classification ( Poster ) > link | YongKyung Oh 路 Dongyoung Lim 路 SUNGIL KIM 馃敆 |
-
|
Enhanced Distribution Modelling via Augmented Architectures For Neural ODE Flows ( Poster ) > link | Etrit Haxholli 路 Marco Lorenzi 馃敆 |
-
|
Does In-Context Operator Learning Generalize to Domain-Shifted Settings? ( Poster ) > link | Jerry Liu 路 N. Benjamin Erichson 路 Kush Bhatia 路 Michael Mahoney 路 Christopher R茅 馃敆 |
-
|
On the Generalization of Deep Neural Networks for Optimal Sensor Placement in Global Ocean Forecasting ( Poster ) > link | Alexander Lobashev 路 Nikita Turko 路 Konstantin Ushakov 路 Maxim Kaurkin 路 Rashit Ibrayev 馃敆 |
-
|
A Holistic Vision: Modeling Patient Trajectories in Longitudinal Medical Imaging ( Poster ) > link | Nico Disch 路 David Zimmerer 馃敆 |
-
|
Solving Noisy Inverse Problems via Posterior Sampling: A Policy Gradient View-Point ( Poster ) > link | Haoyue Tang 路 Tian Xie 路 Aosong Feng 路 Hanyu Wang 路 Chenyang Zhang 路 Yang Bai 馃敆 |
-
|
Neural oscillators for generalizing parametric PDEs ( Poster ) > link | Taniya Kapoor 路 Abhishek Chandra 路 Daniel Tartakovsky 路 Hongrui Wang 路 Alfredo Nunez 路 Rolf Dollevoet 馃敆 |