An overview of multi-agent reinforcement learning from game theoretical perspective
Y Yang, J Wang - arXiv preprint arXiv:2011.00583, 2020 - arxiv.org
Following the remarkable success of the AlphaGO series, 2019 was a booming year that
witnessed significant advances in multi-agent reinforcement learning (MARL) techniques …
witnessed significant advances in multi-agent reinforcement learning (MARL) techniques …
Propagation of chaos: a review of models, methods and applications. I. Models and methods
LP Chaintron, A Diez - arXiv preprint arXiv:2203.00446, 2022 - arxiv.org
The notion of propagation of chaos for large systems of interacting particles originates in
statistical physics and has recently become a central notion in many areas of applied …
statistical physics and has recently become a central notion in many areas of applied …
Deep learning: a statistical viewpoint
The remarkable practical success of deep learning has revealed some major surprises from
a theoretical perspective. In particular, simple gradient methods easily find near-optimal …
a theoretical perspective. In particular, simple gradient methods easily find near-optimal …
The shaped transformer: Attention models in the infinite depth-and-width limit
In deep learning theory, the covariance matrix of the representations serves as aproxy to
examine the network's trainability. Motivated by the success of Transform-ers, we study the …
examine the network's trainability. Motivated by the success of Transform-ers, we study the …
[HTML][HTML] Surprises in high-dimensional ridgeless least squares interpolation
Interpolators—estimators that achieve zero training error—have attracted growing attention
in machine learning, mainly because state-of-the art neural networks appear to be models of …
in machine learning, mainly because state-of-the art neural networks appear to be models of …
Gradient flow dynamics of shallow relu networks for square loss and orthogonal inputs
E Boursier, L Pillaud-Vivien… - Advances in Neural …, 2022 - proceedings.neurips.cc
The training of neural networks by gradient descent methods is a cornerstone of the deep
learning revolution. Yet, despite some recent progress, a complete theory explaining its …
learning revolution. Yet, despite some recent progress, a complete theory explaining its …
Propagation of chaos: a review of models, methods and applications. II. Applications
LP Chaintron, A Diez - arXiv preprint arXiv:2106.14812, 2021 - arxiv.org
The notion of propagation of chaos for large systems of interacting particles originates in
statistical physics and has recently become a central notion in many areas of applied …
statistical physics and has recently become a central notion in many areas of applied …
[HTML][HTML] A selective overview of deep learning
Deep learning has achieved tremendous success in recent years. In simple words, deep
learning uses the composition of many nonlinear functions to model the complex …
learning uses the composition of many nonlinear functions to model the complex …
Mean-field langevin dynamics: Exponential convergence and annealing
L Chizat - arXiv preprint arXiv:2202.01009, 2022 - arxiv.org
Noisy particle gradient descent (NPGD) is an algorithm to minimize convex functions over
the space of measures that include an entropy term. In the many-particle limit, this algorithm …
the space of measures that include an entropy term. In the many-particle limit, this algorithm …
Hierarchies, entropy, and quantitative propagation of chaos for mean field diffusions
D Lacker - Probability and Mathematical Physics, 2023 - msp.org
This paper develops a nonasymptotic, local approach to quantitative propagation of chaos
for a wide class of mean field diffusive dynamics. For a system of n interacting particles, the …
for a wide class of mean field diffusive dynamics. For a system of n interacting particles, the …