Generalization Through The Lens Of Learning Dynamics

Abstract

A machine learning (ML) system must learn not only to match the output of a target function on a training set, but also to generalize to novel situations in order to yield accurate predictions at deployment. In most practical applications, the user cannot exhaustively enumerate every possible input to the model; strong generalization performance is therefore crucial to the development of ML systems which are performant and reliable enough to be deployed in the real world. While generalization is well-understood theoretically in a number of hypothesis classes, the impressive generalization performance of deep neural networks has stymied theoreticians. In deep reinforcement learning (RL), our understanding of generalization is further complicated by the conflict between generalization and stability in widely-used RL algorithms. This thesis will provide insight into generalization by studying the learning dynamics of deep neural networks in both supervised and reinforcement learning tasks

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylyle2022generalization

Related papers

• A Survey Analyzing Generalization In Deep Reinforcement Learning (2024)0.00
• Dynamics Generalization Via Information Bottleneck In Deep Reinforcement Learning (2020)0.00
• Measuring And Characterizing Generalization In Deep Reinforcement Learning (2018)9.76
• Generalizing Skills With Semi-supervised Reinforcement Learning (2016)0.00
• Improving Performance In Reinforcement Learning By Breaking Generalization In Neural Networks (2020)0.00
• Assessing Generalization In Deep Reinforcement Learning (2018)0.00
• Understanding What Affects The Generalization Gap In Visual Reinforcement Learning: Theory And Empirical Evidence (2024)5.84
• Gradient Coupling: The Hidden Barrier To Generalization In Agentic Reinforcement Learning (2025)0.00