Accepted Papers

Title Authors
Time-Reversed Dissipation Induces Duality Between Minimizing Gradient Norm and Function Value (highlighted as contributed talk) Jaeyeon Kim, Asuman E. Ozdaglar, Chanwoo Park, Ernest K. Ryu
Decision-Aware Actor-Critic with Function Approximation and Theoretical Guarantees Sharan Vaswani, Amirreza Kazemi, Reza Babanezhad Harikandeh, Nicolas Le Roux
The Power of Duality Principle in Offline Average-Reward Reinforcement Learning Asuman E. Ozdaglar, Sarath Pattathil, Jiawei Zhang, Kaiqing Zhang
Reward-Based Reinforcement Learning with Risk Constraints Jane Lee, Konstantinos Nikolakakis, Dionysios Kalogerias, Amin Karbasi
A max-affine spline approximation of neural networks using the Legendre transform of a convex-concave representation Adam Perrett, Danny Wood, Gavin Brown
Duality Principle and Biologically Plausible Learning: Connecting the Representer Theorem and Hebbian Learning Yanis Bahroun, Dmitri Chklovskii, Anirvan M. Sengupta
On the Fisher-Rao Gradient of the Evidence Lower Bound Jesse van Oostrum, Nihat Ay
Duality in Multi-View Restricted Kernel Machines Sonny Achten, Arun Pandey, Hannes De Meulemeester, Bart De Moor, Johan Suykens
A Dual Formulation for Probabilistic Principal Component Analysis Henri De Plaen, Johan Suykens
Energy-Based Non-Negative Tensor Factorization via Multi-Body Modeling Kazu Ghalamkari, Mahito Sugiyama
Dual Gauss-Newton Directions for Deep Learning Vincent Roulet, Mathieu Blondel
Controlling the Inductive Bias of Wide Neural Networks by Modifying the Kernel's Spectrum Amnon Geifman, Daniel Barzilai, Ronen Basri, Meirav Galun
Kernel Mirror Prox and RKHS Gradient Flow for Mixed Functional Nash Equilibrium Pavel Dvurechensky, Jia-Jie Zhu
A Representer Theorem for Vector-Valued Neural Networks: Insights on Weight Decay Training and Widths of Deep Neural Networks (highlighted as contributed talk) Joseph Shenouda, Rahul Parhi, Kangwook Lee, Robert D Nowak
RIFLE: Imputation and Robust Inference from Low Order Marginals (highlighted as contributed talk) Sina Baharlouei, Kelechi Ogudu, Peng Dai, Sze-chuan Suen, Meisam Razaviyayn
Estimating Joint interventional distributions from marginal interventional data Sergio Hernan Garrido Mejia, Elke Kirschbaum, Armin Kekić, Atalanti A. Mastakouri
Learning with Primal-Dual Spectral Risk Measures: a Fast Incremental Algorithm Ronak Mehta, Vincent Roulet, Krishna Pillutla, Zaid Harchaoui
Implicit Interpretation of Importance Weight Aware Updates Keyi Chen, Francesco Orabona
The Memory-Perturbation Equation: Understanding Model's Sensitivity to Data Peter Nickl, Lu Xu, Dharmesh Tailor, Thomas Möllenhoff, Mohammad Emtiyaz Khan
Memory Maps to Understand Models Dharmesh Tailor, Paul Edmund Chang, Siddharth Swaroop, Eric Nalisnick, Arno Solin, Mohammad Emtiyaz Khan
Sparse Function-Space Representation of Neural Networks Aidan Scannell, Riccardo Mereu, Paul Edmund Chang, Ella Tamir, Joni Pajarinen, Arno Solin