708 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- GSI Helmholtz Centre for Heavy Ion ResearchDE38 papers
- Justus-Liebig-Universität GießenDE19 papers
- Goethe University FrankfurtDE18 papers
- Technische Universität DarmstadtDE17 papers
- Friedrich-Alexander-Universität Erlangen-NürnbergDE15 papers
- Johannes Gutenberg University MainzDE13 papers
- Helmholtz Institute MainzDE10 papers
- Centre National de la Recherche ScientifiqueFR9 papers
- Institute for Theoretical and Experimental PhysicsRU9 papers
- National Research Nuclear University MEPhIRU9 papers
- European Organization for Nuclear ResearchCH8 papers
- Institut National de Physique Nucléaire et de Physique des ParticulesFR8 papers
5 papers · 1 filter
On the duality between contrastive and non-contrastive self-supervised learning
Quentin Garrido, Yubei Chen, Adrien Bardes +2
Recent approaches in self-supervised learning of image representations can be categorized into different families of methods and, in particular, can be divided into contrastive and…
Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding
Yangjun Ruan, Karen Ullrich, Daniel Severo +5
Latent variable models have been successfully applied in lossless compression with the bits-back coding algorithm. However, bits-back suffers from an increase in the bitrate equal…
Understanding self-supervised Learning Dynamics without Contrastive Pairs
Yuandong Tian, Xinlei Chen, Surya Ganguli
While contrastive approaches of self-supervised learning (SSL) learn representations by minimizing the distance between two augmented views of the same data point (positive pairs)…
Risk-Sensitive Generative Adversarial Imitation Learning
Jonathan Lacotte, Mohammad Ghavamzadeh, Yinlam Chow +1
We study risk-sensitive imitation learning where the agent's goal is to perform at least as well as the expert in terms of a risk profile. We first formulate our risk-sensitive imi…
AdaBatch: Efficient Gradient Aggregation Rules for Sequential and Parallel Stochastic Gradient Methods
Alexandre Défossez, Francis Bach
We study a new aggregation operator for gradients coming from a mini-batch for stochastic gradient (SG) methods that allows a significant speed-up in the case of sparse optimizatio…