Cover Image

Directions of Curvature as an Explanation for Loss of Plasticity

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lewandowski, Alex, Tanaka, Haruto, Schuurmans, Dale, Machado, Marlos C.
Format:	Preprint
Published:	2023
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Plastic Learning with Deep Fourier Features
by: Lewandowski, Alex, et al.
Published: (2024)

Learning Continually by Spectral Regularization
by: Lewandowski, Alex, et al.
Published: (2024)

Universal computation is intrinsic to language model decoding
by: Lewandowski, Alex, et al.
Published: (2026)

Reinforcement Teaching
by: Muslimani, Calarina, et al.
Published: (2022)

A Unified Noise-Curvature View of Loss of Trainability
by: Baveja, Gunbir Singh, et al.
Published: (2025)

The World Is Bigger! A Computationally-Embedded Perspective on the Big World Hypothesis
by: Lewandowski, Alex, et al.
Published: (2025)

A Study of Value-Aware Eigenoptions
by: Kotamreddy, Harshil, et al.
Published: (2025)

The Laplacian Keyboard: Beyond the Linear Span
by: Chandrasekar, Siddarth, et al.
Published: (2026)

DROGO: Default Representation Objective via Graph Optimization in Reinforcement Learning
by: Tse, Hon Tik, et al.
Published: (2026)

Spectral Ghost in Representation Learning: from Component Analysis to Self-Supervised Learning
by: Dai, Bo, et al.
Published: (2026)

Learning to Reason Efficiently with Discounted Reinforcement Learning
by: Ayoub, Alex, et al.
Published: (2025)

Rectifying Regression in Reinforcement Learning
by: Ayoub, Alex, et al.
Published: (2025)

Averaging $n$-step Returns Reduces Variance in Reinforcement Learning
by: Daley, Brett, et al.
Published: (2024)

Reward-Aware Proto-Representations in Reinforcement Learning
by: Tse, Hon Tik, et al.
Published: (2025)

Toward Understanding In-context vs. In-weight Learning
by: Chan, Bryan, et al.
Published: (2024)

Proper Laplacian Representation Learning
by: Gomez, Diego, et al.
Published: (2023)

Harnessing Discrete Representations For Continual Reinforcement Learning
by: Meyer, Edan, et al.
Published: (2023)

Deep Double Q-learning
by: Nagarajan, Prabhat, et al.
Published: (2025)

Demystifying the Recency Heuristic in Temporal-Difference Learning
by: Daley, Brett, et al.
Published: (2024)

Trajectory-Aware Eligibility Traces for Off-Policy Reinforcement Learning
by: Daley, Brett, et al.
Published: (2023)

Laplacian Representations for Decision-Time Planning
by: Shehmar, Dikshant, et al.
Published: (2026)

AGaLiTe: Approximate Gated Linear Transformers for Online Reinforcement Learning
by: Pramanik, Subhojeet, et al.
Published: (2023)

An Analysis of Action-Value Temporal-Difference Methods That Learn State Values
by: Daley, Brett, et al.
Published: (2025)

Managing Temporal Resolution in Continuous Value Estimation: A Fundamental Trade-off
by: Zhang, Zichen, et al.
Published: (2022)

Provable Representation with Efficient Planning for Partial Observable Reinforcement Learning
by: Zhang, Hongming, et al.
Published: (2023)

Spectral Representation-based Reinforcement Learning
by: Gao, Chenxiao, et al.
Published: (2025)

Soft Preference Optimization: Aligning Language Models to Expert Distributions
by: Sharifnassab, Arsalan, et al.
Published: (2024)

Ordering-based Conditions for Global Convergence of Policy Gradient Methods
by: Mei, Jincheng, et al.
Published: (2025)

Stochastic Gradient Succeeds for Bandits
by: Mei, Jincheng, et al.
Published: (2024)

Disentangling the Causes of Plasticity Loss in Neural Networks
by: Lyle, Clare, et al.
Published: (2024)

Curvature Clues: Decoding Deep Learning Privacy with Input Loss Curvature
by: Ravikumar, Deepak, et al.
Published: (2024)

Curvature-Aligned Probing for Local Loss-Landscape Stabilization
by: Kiselev, Nikita, et al.
Published: (2026)

Neural Network Plasticity and Loss Sharpness
by: Koster, Max, et al.
Published: (2024)

Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates
by: Mei, Jincheng, et al.
Published: (2025)

Newton Losses: Using Curvature Information for Learning with Differentiable Algorithms
by: Petersen, Felix, et al.
Published: (2024)

From Memorization to Reasoning in the Spectrum of Loss Curvature
by: Merullo, Jack, et al.
Published: (2025)

Deep Reinforcement Learning with Gradient Eligibility Traces
by: Elelimy, Esraa, et al.
Published: (2025)

On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature
by: Zhang, Yikuan, et al.
Published: (2026)

Learning to Forget: Continual Learning with Adaptive Weight Decay
by: Ramesh, Aditya A., et al.
Published: (2026)

Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning
by: Elsayed, Mohamed, et al.
Published: (2024)