research
∙
02/09/2023
The Edge of Orthogonality: A Simple View of What Makes BYOL Tick
Self-predictive unsupervised learning methods such as BYOL or SimSiam ha...
share
research
∙
01/12/2023
SemPPL: Predicting pseudo-labels for better contrastive representations
Learning from large amounts of unsupervised data and a small amount of s...
research
∙
11/28/2022
Continuous diffusion for categorical data
Diffusion models have quickly become the go-to paradigm for generative m...
research
∙
10/26/2022
Categorical SDEs with Simplex Diffusion
Diffusion models typically operate in the standard framework of generati...
research
∙
03/15/2022
Zipfian environments for Reinforcement Learning
As humans and animals learn in the natural world, they encounter distrib...
research
∙
10/20/2020
BYOL works even without batch statistics
Bootstrap Your Own Latent (BYOL) is a self-supervised learning approach ...
research
∙
06/13/2020
Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning
We introduce Bootstrap Your Own Latent (BYOL), a new approach to self-su...
research
∙
11/25/2019
Biologically inspired architectures for sample-efficient deep reinforcement learning
Deep reinforcement learning requires a heavy price in terms of sample ef...
research
∙
05/03/2019
Static Activation Function Normalization
Recent seminal work at the intersection of deep neural networks practice...
research
∙
02/07/2019
Combining learning rate decay and weight decay with complexity gradient descent - Part I
The role of L^2 regularization, in the specific case of deep neural netw...
research
∙
12/22/2017
A short variational proof of equivalence between policy gradients and soft Q learning
Two main families of reinforcement learning algorithms, Q-learning and p...
research
∙
12/19/2017