output
20142023
most citedBootstrap your own latent: A new approach to self-supervised Learning

3.4k citations

Showing stat.MLShow all

18 papers · 1 filter

stat.ML2022

Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees

Daniil Tiapkin, Denis Belomestny, Daniele Calandriello +6

We consider reinforcement learning in an environment modeled by an episodic, finite, stage-dependent Markov decision process of horizon with states, and actions. The pe…

stat.ML20221 cited

Scaling Gaussian Process Optimization by Evaluating a Few Unique Candidates Multiple Times

Daniele Calandriello, Luigi Carratino, Alessandro Lazaric +2

Computing a Gaussian process (GP) posterior has a computational cost cubical in the number of historical points. A reformulation of the same GP posterior highlights that this compl…

stat.ML2021

Discretization Drift in Two-Player Games

Mihaela Rosca, Yan Wu, Benoit Dherin +1

Gradient-based methods for two-player games produce rich dynamics that can solve challenging problems, yet can be difficult to stabilize and understand. Part of this complexity ori…

stat.ML20214 cited

Order Matters: Probabilistic Modeling of Node Sequence for Graph Generation

Xiaohui Chen, Xu Han, Jiajing Hu +2

A graph generative model defines a distribution over graphs. One type of generative model is constructed by autoregressive neural networks, which sequentially add nodes and edges t…

stat.ML20212 cited

Model-Free Learning for Two-Player Zero-Sum Partially Observable Markov Games with Perfect Recall

Tadashi Kozuno, Pierre Ménard, Rémi Munos +1

We study the problem of learning a Nash equilibrium (NE) in an imperfect information game (IIG) through self-play. Precisely, we focus on two-player, zero-sum, episodic, tabular II…

stat.ML202127 cited

NeRF-VAE: A Geometry Aware 3D Scene Generative Model

Adam R. Kosiorek, Heiko Strathmann, Daniel Zoran +4

We propose NeRF-VAE, a 3D scene generative model that incorporates geometric structure via NeRF and differentiable volume rendering. In contrast to NeRF, our model takes into accou…