learning dynamics

Convergence of No-Swap-Regret Dynamics in Self-Play NeurIPS 2024 Dynamics of Supervised and Reinforcement Learning in the Non-Linear Perceptron NeurIPS 2024 Efficient Low-Dimensional Compression of Overparameterized Models AISTATS 2024 Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space NeurIPS 2024 Equilibrium Computation in Multidimensional Congestion Games: CSP and Learning Dynamics Approaches UAI 2024 Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning NeurIPS 2024 Initializing Services in Interactive ML Systems for Diverse Users NeurIPS 2024 Local to Global: Learning Dynamics and Effect of Initialization for Transformers NeurIPS 2024 Memory Asymmetry Creates Heteroclinic Orbits to Nash Equilibrium in Learning in Zero-Sum Games AAAI 2024 Model Based Inference of Synaptic Plasticity Rules NeurIPS 2024 Parameter Symmetry and Noise Equilibrium of Stochastic Gradient Descent NeurIPS 2024 Separation and Bias of Deep Equilibrium Models on Expressivity and Learning Dynamics NeurIPS 2024 Team-Fictitious Play for Reaching Team-Nash Equilibrium in Multi-team Games NeurIPS 2024 The Ladder in Chaos: Improving Policy Learning by Harnessing the Parameter Evolving Path in A Low-dimensional Space NeurIPS 2024 Understanding and Leveraging the Learning Phases of Neural Networks AAAI 2024 Why Do Animals Need Shaping? A Theory of Task Composition and Curriculum Learning ICML 2024 A Pair-Approximation Method for Modelling the Dynamics of Multi-Agent Stochastic Games AAAI 2023 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 Flexible Phase Dynamics for Bio-Plausible Contrastive Learning ICML 2023 Leveraging the two-timescale regime to demonstrate convergence of neural networks NeurIPS 2023 Loss Dynamics of Temporal Difference Reinforcement Learning NeurIPS 2023 On The Specialization of Neural Modules ICLR 2023 Reparameterization through Spatial Gradient Scaling ICLR 2023 Stochastic Gradient Descent-Induced Drift of Representation in a Two-Layer Neural Network ICML 2023