Image de couverture de livre

Replay Can Provably Increase Forgetting

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Mahdaviyeh, Yasaman, Lucas, James, Ren, Mengye, Tolias, Andreas S., Zemel, Richard, Pitassi, Toniann
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Distribution-Free Statistical Dispersion Control for Societal Applications
par: Deng, Zhun, et autres
Publié: (2023)

Improving Predictor Reliability with Selective Recalibration
par: Zollo, Thomas P., et autres
Publié: (2024)

Prompt Risk Control: A Rigorous Framework for Responsible Deployment of Large Language Models
par: Zollo, Thomas P., et autres
Publié: (2023)

Poly-attention: a general scheme for higher-order self-attention
par: Chakrabarti, Sayak, et autres
Publié: (2026)

Every Bit Counts: A Theoretical Study of Precision-Expressivity Tradeoffs in Quantized Transformers
par: Chakrabarti, Sayak, et autres
Publié: (2026)

Differential privacy from axioms
par: Blanc, Guy, et autres
Publié: (2025)

Integrating Present and Past in Unsupervised Continual Learning
par: Zhang, Yipeng, et autres
Publié: (2024)

Learning and Forgetting Unsafe Examples in Large Language Models
par: Zhao, Jiachen, et autres
Publié: (2023)

Seeking the Unfamiliar but Memorable: Conceptual Creativity as Meta-Learning
par: Ren, Mengye
Publié: (2026)

Online Algorithmic Recourse by Collective Action
par: Creager, Elliot, et autres
Publié: (2023)

Forgetting in Language Models: Capacity, Optimization, and Self-Generated Replay
par: Marek, Martin, et autres
Publié: (2026)

Local Reinforcement Learning with Action-Conditioned Root Mean Squared Q-Functions
par: Wu, Frank, et autres
Publié: (2025)

Eidetic Learning: an Efficient and Provable Solution to Catastrophic Forgetting
par: Dronen, Nicholas, et autres
Publié: (2025)

Confidence Calibration in Vision-Language-Action Models
par: Zollo, Thomas P, et autres
Publié: (2025)

Midway Network: Learning Representations for Recognition and Motion from Latent Dynamics
par: Hoang, Christopher, et autres
Publié: (2025)

Memory Storyboard: Leveraging Temporal Segmentation for Streaming Self-Supervised Learning from Egocentric Videos
par: Yang, Yanlai, et autres
Publié: (2025)

Unsupervised Confidence Calibration for Reasoning LLMs from a Single Generation
par: Zollo, Thomas, et autres
Publié: (2026)

Few-Shot Design Optimization by Exploiting Auxiliary Information
par: Mani, Arjun, et autres
Publié: (2026)

CORE: Mitigating Catastrophic Forgetting in Continual Learning through Cognitive Replay
par: Zhang, Jianshu, et autres
Publié: (2024)

Logits Replay + MoClip: Stabilized, Low-Cost Post-Training with Minimal Forgetting
par: Qiu, Suming, et autres
Publié: (2025)

Adapt or Forget: Provable Tradeoffs Between Adam and SGD in Nonstationary Optimization
par: Sahu, Sharan, et autres
Publié: (2026)

Defense without Forgetting: Continual Adversarial Defense with Anisotropic & Isotropic Pseudo Replay
par: Zhou, Yuhang, et autres
Publié: (2024)

In-Context Clustering with Large Language Models
par: Wang, Ying, et autres
Publié: (2025)

Replay-and-Forget-Free Graph Class-Incremental Learning: A Task Profiling and Prompting Approach
par: Niu, Chaoxi, et autres
Publié: (2024)

Provable Effects of Data Replay in Continual Learning: A Feature Learning Perspective
par: Ding, Meng, et autres
Publié: (2026)

Tell Me What To Learn: Generalizing Neural Memory to be Controllable in Natural Language
par: Bennett, Max S., et autres
Publié: (2026)

Test-Time Warmup for Multimodal Large Language Models
par: Rajaneesh, Nikita, et autres
Publié: (2025)

Catastrophic Forgetting Mitigation via Discrepancy-Weighted Experience Replay
par: Xu, Xinrun, et autres
Publié: (2025)

May the Forgetting Be with You: Alternate Replay for Learning with Noisy Labels
par: Millunzi, Monica, et autres
Publié: (2024)

KoReA-SFL: Knowledge Replay-based Split Federated Learning Against Catastrophic Forgetting
par: Xia, Zeke, et autres
Publié: (2024)

FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learning
par: Feng, Yujie, et autres
Publié: (2026)

LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos
par: Wang, Ying, et autres
Publié: (2023)

Are LLMs Prescient? A Continuous Evaluation using Daily News as the Oracle
par: Dai, Hui, et autres
Publié: (2024)

Fully-Fluctuating Participation in Sleepy Consensus
par: Efron, Yuval, et autres
Publié: (2025)

Federated Learning Under Temporal Drift -- Mitigating Catastrophic Forgetting via Experience Replay
par: Kokkula, Sahasra, et autres
Publié: (2026)

Continual Learning: Less Forgetting, More OOD Generalization via Adaptive Contrastive Replay
par: Rezaei, Hossein, et autres
Publié: (2024)

Provably effective detection of effective data poisoning attacks
par: Gallagher, Jonathan, et autres
Publié: (2025)

TFGN: Task-Free, Replay-Free Continual Pre-Training Without Catastrophic Forgetting at LLM Scale
par: Ganguli, Anurup
Publié: (2026)

Malign Overfitting: Interpolation Can Provably Preclude Invariance
par: Wald, Yoav, et autres
Publié: (2022)

Level Up: Defining and Exploiting Transitional Problems for Curriculum Learning
par: Tang, Zhenwei, et autres
Publié: (2026)