EPFL @ NeurIPS 2022
41 EPFL papers have been accepted to this year conference on Neural Information Processing Systems (NeurIPS).
36th edition of NeurIPS will take e place in New Orleans, USA from November 27th to December 3rd, 2022.
We would like to congratulate all the authors for their excellent work!
List of the EPFL accepted papers:
- Identifiability and generalizability from multiple experts in Inverse Reinforcement Learning by Paul Rolland, Luca Viano, Norman Schuerhoff, Boris Nikolov, Volkan Cevher
- Understanding Deep Neural Function Approximation in Reinforcement Learning via ε-Greedy Exploration by Fanghui Liu, Luca Viano, Volkan Cevher
- No-regret learning in games with noisy feedback: Faster rates and adaptivity via learning rate separation by Yu-Guan Hsieh, Kimon Antonakopoulos, Volkan Cevher, Panayotis Mertikopoulos
- On the Double Descent of Random Features Models Trained with SGD by Fanghui Liu, Johan Suykens, Volkan Cevher
- A First Approach to Universal Second-Order Acceleration for Convex Minimization by Ali Kavis, Kimon Antonakopoulos, Volkan Cevher
- Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization) by Zhenyu Zhu, Fanghui Liu, Grigorios Chrysos, Volkan Cevher
- Sound and Complete Verification of Polynomial Networks by Elias Abad Rocamora, Mehmet Fatih Sahin, Fanghui Liu, Grigorios Chrysos, Volkan Cevher
- Proximal Point Imitation Learning by Luca Viano, Angeliki Kamoutsi, Gergely Neu, Igor Krawczuk, Volkan Cevher
- Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study by Yongtao Wu, Zhenyu Zhu, Fanghui Liu, Grigorios Chrysos, Volkan Cevher
- Generalization Properties of NAS under Activation and Skip Connection Search by Zhenyu Zhu, Fanghui Liu, Grigorios Chrysos, Volkan Cevher
- Adaptive Stochastic Variance Reduction for Non-convex Finite-Sum Minimization by Ali Kavis, Efstration Panteleimon Skoulakis, Kimon Antonakopoulos, Leello Tadesse Dadi, Volkan Cevher
- Learning sparse features can lead to overfitting in neural networks by Leonardo Petrini, Francesco Cagnetta, Eric Vanden-Eijnden, Matthieu Wyart
- Low-rank lottery tickets: finding efficient low-rank neural networks via matrix differential equations by Steffen Schotthöfer, Emanuele Zangrando, Jonas Kusch, Gianluca Ceruti, Francesco Tudisco
- Deep Bidirectional Language-Knowledge Pretraining by Michihiro Yasunaga, Antoine Bosselut, Hongyu Ren, Xikun Zhang, Christopher D Manning, Percy Liang, Jure Leskovec
- Phase diagram of Stochastic Gradient Descent in high-dimensional two-layer neural networks by Rodrigo Veiga, Ludovic Stephan, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová
- Subspace clustering in high-dimensions: Phase transitions & Statistical-to-Computational gap by Luca Pesce, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová
- Multi-layer State Evolution Under Random Convolutional Design by Max Daniels, Cédric Gerbelot, Florent Krzakala, Lenka Zdeborová
- Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learning by Anastasia Koloskova, Sebastian U. Stich, Martin Jaggi
- Beyond spectral gap: The role of the topology in decentralized learning by Thijs Vogels, Hadrien Hendrikx, Martin Jaggi
- Decentralized local stochastic extra-gradient for variational inequalities by Aleksandr Beznosikov, Pavel Dvurechensky, Anastasia Koloskova, Valentin Samokhin, Sebastian U Stich, Alexander Gasnikov
- Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs by Etienne Boursier, Loucas Pillaud-Vivien, Nicolas Flammarion
- Stochastic Second-Order Methods Provably Beat SGD For Gradient-Dominated Functions by Mohammadsaeed Masiha · Saber Salehkaleybar · Niao He · Negar Kiyavash · Patrick Thiran
- Sharp Analysis of Stochastic Optimization under Global Kurdyka-Lojasiewicz Inequality by Jalal Etesami · Ilyas Fatkhullin · Niao He · Negar Kiyavash
- Causal Discovery in Linear Latent Variable Models Subject to Measurement Error by Yuqin Yang · AmirEmad Ghassami · Mohamed Nafea · Negar Kiyavash · Kun Zhang · Ilya Shpitser
- Trajectory Inference via Mean-field Langevin in Path Space by Lénaïc Chizat, Stephen Zhang, Matthieu Heitz, Geoffrey Schiebinger
- Generalised Implicit Neural Representations by Daniele Grattarola · Pierre Vandergheynst
- DMAP: a Distributed Morphological Attention Policy for learning to locomote with a changing body by Alberto Chiappa · Alessandro Marin Vargas · Alexander Mathis
- On the non-universality of deep learning: quantifying the cost of symmetry by Emmanuel Abbe · Enric Boix-Adsera
- Learning to Reason with Neural Networks: Generalization, Unseen Data and Boolean Measures by Emmanuel Abbe · Samy Bengio · Elisabetta Cornacchia · Jon Kleinberg · Aryo Lotfi · Maithra Raghu · Chiyuan Zhang
- Kernel Attractor Networks: A Unifying Framework for Memory Modeling by Georgios Iatropoulos · Johanni Brea · Wulfram Gerstner
- Mesoscopic modeling of hidden spiking neurons by Shuqi Wang · Valentin Schmutz · Guillaume Bellec · Wulfram Gerstner
- Feature Learning in L2-regularized DNNs: Attraction/Repulsion and Sparsity by Arthur Jacot · Eugene Golikov · Clement Hongler · Franck Gabriel
- Towards Consistency in Adversarial Classification by Laurent Meunier, Raphael Ettedgui, Rafael Pinot, Yann Chevaleyre, Jamal Atif
- Neural Set Function Extensions: Learning with Discrete Functions in High Dimensions by Nikolaos Karalias, Joshua Robinson, Andreas Loukas, Stefanie Jegelka
- Beyond Time-Average Convergence: Near-Optimal Uncoupled Online Learning via Clairvoyant Multiplicative Weights Update by Georgios Piliouras, Ryan Simm, Stratis Skoulakis
- Contact-aware Human Motion Forecasting by Wei Mao, Miaomiao Liu, Richard Hartley, Mathieu Salzmann
- Robust Binary Models by Pruning Randomly-initialized Networks by Chen Liu, Ziqi Zhao, Sabine Süsstrunk, Mathieu Salzmann
- Non-Gaussian Tensor Programs by Greg Yang and Eugene Golikov
- FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Settings by Jean Ogier du Terrail · Samy-Safwan Ayed · Edwige Cyffers · Felix Grimberg · Chaoyang He · Regis Loeb · Paul Mangold · Tanguy Marchand · Othmane Marfoq · Erum Mushtaq · Boris Muzellec · Constantin Philippenko · Santiago Silva · Maria Teleńczuk · Shadi Albarqouni · Salman Avestimehr · Aurélien Bellet · Aymeric Dieuleveut · Martin Jaggi · Sai Praneeth Karimireddy · Marco Lorenzi · Giovanni Neglia · Marc Tommasi · Mathieu Andreux
- Task Discovery: Finding the Tasks that Neural Networks Generalize on by Andrei Atanov, Andrey Filatov, Teresa Yeo, Ajay Sohmshetty, Amir Zamir
- PALMER: Perception-Action Loop with Memory Reorganization for Planning by Onur Beker, Mohammad Mohammadi, Amir Zamir