Cover Image

More Than Memory Savings: Zeroth-Order Optimization Mitigates Forgetting in Continual Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yu, Wanhao, Wang, Zheng, Niu, Shuteng, Lin, Sen, Yang, Li
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ZOTTA: Test-Time Adaptation with Gradient-Free Zeroth-Order Optimization
by: Zhang, Ronghao, et al.
Published: (2026)

Forget Less, Retain More: A Lightweight Regularizer for Rehearsal-Based Continual Learning
by: Alssum, Lama, et al.
Published: (2025)

Continual Learning: Less Forgetting, More OOD Generalization via Adaptive Contrastive Replay
by: Rezaei, Hossein, et al.
Published: (2024)

Preventing Catastrophic Forgetting through Memory Networks in Continuous Detection
by: Bhatt, Gaurav, et al.
Published: (2024)

ConceptGuard: Continual Personalized Text-to-Image Generation with Forgetting and Confusion Mitigation
by: Guo, Zirun, et al.
Published: (2025)

Continual Learning of Achieving Forgetting-free and Positive Knowledge Transfer
by: Wang, Zhi, et al.
Published: (2026)

Adversarially Diversified Rehearsal Memory (ADRM): Mitigating Memory Overfitting Challenge in Continual Learning
by: Khan, Hikmat, et al.
Published: (2024)

How Weight Resampling and Optimizers Shape the Dynamics of Continual Learning and Forgetting in Neural Networks
by: Frati, Lapo, et al.
Published: (2025)

Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning
by: Lou, Meng, et al.
Published: (2026)

A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning
by: Wang, Zhenyi, et al.
Published: (2023)

Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting
by: Liu, Yuyang, et al.
Published: (2025)

Knowledge Accumulation in Continually Learned Representations and the Issue of Feature Forgetting
by: Hess, Timm, et al.
Published: (2023)

Fine-tuning Quantized Neural Networks with Zeroth-order Optimization
by: Shang, Sifeng, et al.
Published: (2025)

BB-Patch: BlackBox Adversarial Patch-Attack using Zeroth-Order Optimization
by: Kumar, Satyadwyoom, et al.
Published: (2024)

Fine-tuning MLLMs Without Forgetting Is Easier Than You Think
by: Li, He, et al.
Published: (2026)

Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent
by: Wu, Junda, et al.
Published: (2025)

Slowing Down Forgetting in Continual Learning
by: Janetzky, Pascal, et al.
Published: (2024)

Merging without Forgetting: Continual Fusion of Task-Specific Models via Optimal Transport
by: Pan, Zecheng, et al.
Published: (2025)

Branch, or Layer? Zeroth-Order Optimization for Continual Learning of Vision-Language Models
by: Liu, Ziwei, et al.
Published: (2025)

Sculpting Memory: Multi-Concept Forgetting in Diffusion Models via Dynamic Mask and Concept-Aware Optimization
by: Li, Gen, et al.
Published: (2025)

Forget Many, Forget Right: Scalable and Precise Concept Unlearning in Diffusion Models
by: Deng, Kaiyuan, et al.
Published: (2026)

Diffusion-Driven Data Replay: A Novel Approach to Combat Forgetting in Federated Class Continual Learning
by: Liang, Jinglin, et al.
Published: (2024)

Continual Learning and Catastrophic Forgetting
by: van de Ven, Gido M., et al.
Published: (2024)

Catastrophic Forgetting Mitigation via Discrepancy-Weighted Experience Replay
by: Xu, Xinrun, et al.
Published: (2025)

Rethinking Continual Anomaly Detection on the Edge: Benchmarking Under Realistic Industrial Conditions
by: Weatherly, Chad, et al.
Published: (2026)

Robust Continual Unlearning against Knowledge Erosion and Forgetting Reversal
by: Park, Eun-Ju, et al.
Published: (2026)

Learning to Learn without Forgetting using Attention
by: Vettoruzzo, Anna, et al.
Published: (2024)

Intermediate Outputs Are More Sensitive Than You Think
by: Huang, Tao, et al.
Published: (2024)

Continual Learning: Forget-free Winning Subnetworks for Video Representations
by: Kang, Haeyong, et al.
Published: (2023)

C-Flat++: Towards a More Efficient and Powerful Framework for Continual Learning
by: Li, Wei, et al.
Published: (2025)

An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels
by: Nguyen, Duy-Kien, et al.
Published: (2024)

Continuous Subspace Optimization for Continual Learning
by: Cheng, Quan, et al.
Published: (2025)

Learning without Forgetting for Vision-Language Models
by: Zhou, Da-Wei, et al.
Published: (2023)

Learning without Isolation: Pathway Protection for Continual Learning
by: Chen, Zhikang, et al.
Published: (2025)

BM-CL: Bias Mitigation through the lens of Continual Learning
by: Mansilla, Lucas, et al.
Published: (2025)

Exploring How Generative MLLMs Perceive More Than CLIP with the Same Vision Encoder
by: Li, Siting, et al.
Published: (2024)

Forget Less by Learning Together through Concept Consolidation
by: Kaushik, Arjun Ramesh, et al.
Published: (2026)

ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think
by: Feng, Tao, et al.
Published: (2025)

Rethinking Continual Learning with Progressive Neural Collapse
by: Wang, Zheng, et al.
Published: (2025)

When a Relation Tells More Than a Concept: Exploring and Evaluating Classifier Decisions with CoReX
by: Finzel, Bettina, et al.
Published: (2024)