WASP researchers and PhD students present 15 papers at NeurIPS 2023

The Annual Conference on Neural Information Processing Systems (NeurIPS) is one of the most prestigious and competitive international conferences in machine learning and computational neuroscience. A total of 15 papers by WASP researchers and PhD students have been accepted to NeurIPS 2023. Two of them have been selected as spotlight presentations.

This number is a true success for the program and a mark of excellence.

The list of accepted papers was updated November 2, 2023. The added paper is marked with an asterisk (*).

Accepted papers

Georg Bökman and Fredrik Kahl. “Investigating how ReLU-networks encode symmetries”*

Lennert De Smet, Emanuele Sansone, and Pedro dos Martires. “Differentiable Sampling of Categorical Distributions Using the CatLog-Derivative Trick”

Carl Hvarfner, Erik Hellsten, Frank Hutter, and Luigi Nardi. “Self-Correcting Bayesian Optimization through Bayesian Active Learning”.

Jacob Lindbäck, Zesen Wang and Mikael Johansson. “Bringing regularized optimal transport to lightspeed: a splitting method adapted for GPUs”.

Neeratyoy Mallik, Carl Hvarfner, Edward Bergman, Danny Stoll, Maciej Janowski, Marius Lindauer, Luigi Nardi, and Frank Hutter. “PriorBand: Practical Hyperparameter Optimization in the Age of Deep Learning”.

Hoomaan Maskan, Konstantinos C. Zygalakis, and Alp Yurtsever. ”A Variational Perspective on High-Resolution ODEs”.

Leonard Papenmeier, Luigi Nardi, and Matthias Poloczek. “Bounce: a Reliable Bayesian Optimization Algorithm for Combinatorial and Mixed Spaces”.

Antonio H. Ribeiro, Dave Zachariah, Francis Bach, and Thomas B. Schön. Regularization properties of adversarially-trained linear regression. (Spotlight presentation)

Alessio Russo and Alexandre Proutiere. “Model-free active exploration in Reinforcement Learning”.

Mathias Schreiner, Ole Winther, and Simon Olsson. “Implicit Transfer Operator Learning: Multiple Time-Resolution Surrogates for Molecular Dynamics”.

Stefan Stojanovic, Yassir Jedra, and Alexandre Proutiere. ”Spectral entry-wise matrix estimation for low-rank Reinforcement Learning”.

Ruo-Chun Tzeng, Po-An Wang, and Alexandre Proutiere, Chi-Jen Lu. “Closing the statistical-computational gap in best arm identification in combinatorial bandits”.

Filippo Vannella, Alexandre Proutiere, and Jaeseong Jeong. ”Statistical and computational trade-off in multi-agent multi-armed bandits”.

Po-An Wang, Ruo-Chun Tzeng, and Alexandre Proutiere. “Best arm identification with fixed budget: A large deviation perspective”. (Spotlight presentation)

Yushan Zhang, Johan Edstedt, Bastian Wandt, Per-Erik Forssén, Maria Magnusson, and Michael Felsberg. “GMSF: Global Match Scene Flow”.