conftrace_

learning dynamics

75 papers

Explore in graph

Co-occurring keywords

neural network (6616) game theory (854) representation learning (6206) gradient descent (1144) nash equilibrium (398) neural network optimization (1293) stochastic gradient descent (1091) multi-agent system (1819) transfer learning (5449) zero-sum game (190)

Papers

Understanding and Leveraging the Learning Phases of Neural Networks AAAI 2024
A Theoretical Analysis of the Learning Dynamics under Class Imbalance ICML 2023
Beyond Strict Competition: Approximate Convergence of Multi-agent Q-Learning Dynamics IJCAI 2023
A Pair-Approximation Method for Modelling the Dynamics of Multi-Agent Stochastic Games AAAI 2023
Transformers learn through gradual rank increase NIPS 2023
Unraveling Feature Extraction Mechanisms in Neural Networks EMNLP 2023
Leveraging the two-timescale regime to demonstrate convergence of neural networks NIPS 2023
Loss Dynamics of Temporal Difference Reinforcement Learning NIPS 2023
Stochastic Gradient Descent-Induced Drift of Representation in a Two-Layer Neural Network ICML 2023
Flexible Phase Dynamics for Bio-Plausible Contrastive Learning ICML 2023
The Neural Race Reduction: Dynamics of Abstraction in Gated Networks ICML 2022
Wide Neural Networks Forget Less Catastrophically ICML 2022
Data Augmentation as Feature Manipulation ICML 2022
On Last-Iterate Convergence Beyond Zero-Sum Games ICML 2022
A Few More Examples May Be Worth Billions of Parameters EMNLP 2022
Characterizing Datapoints via Second-Split Forgetting NIPS 2022
Exact learning dynamics of deep linear networks with prior knowledge NIPS 2022
Learning dynamics of deep linear networks with multiple pathways NIPS 2022
On the Dynamics of Gender Learning in Speech Translation NAACL 2022
Convergence Rates of Non-Convex Stochastic Gradient Descent Under a Generic Lojasiewicz Condition and Local Smoothness ICML 2022
Uncoupled Learning Dynamics with $O(\log T)$ Swap Regret in Multiplayer Games NIPS 2022
Follow-the-Regularized-Leader Routes to Chaos in Routing Games ICML 2021
Curriculum Learning by Optimizing Learning Dynamics AISTATS 2021
Online Optimization in Games via Control Theory: Connecting Regret, Passivity and Poincaré Recurrence ICML 2021
Deep Learning Through the Lens of Example Difficulty NIPS 2021