No article text was recorded for this version.
loss landscape flattening (flat minima optimization)
Version 2 of 281 papers113 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Understanding the Role of Training Regimes in Continual Learning
- Blog: Rehearsal revealed: The limits and merits of revisiting samples in continual learning
- Blog: Multi-Task Cooperative Learning via Searching for Flat Minima
- Blog: More Than Memory Savings: Zeroth-Order Optimization Mitigates Forgetting in Continual Learning
- Blog: Incorporating neuro-inspired adaptability for continual learning in artificial intelligence
- Blog: Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima
- Blog: Semi-supervised Drifted Stream Learning with Short Lookback
- Blog: Task Agnostic Representation Consolidation: a Self-supervised based Continual Learning Approach
- Blog: ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think
- Blog: Class-Incremental Continual Learning into the eXtended DER-verse
- Blog: MT-CooL: Multi-Task Cooperative Learning via Flat Minima Searching
- Blog: AlterSGD: Finding Flat Minima for Continual Learning by Alternative Training
- Blog: SharpSeq: Empowering Continual Event Detection through Sharpness-Aware Sequential-task Learning
- Blog: Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
- Blog: Merge to Remember: Sharpness-Aware Isotropic Merging for Continual Learning
- Blog: Flattening Sharpness for Dynamic Gradient Projection Memory Benefits Continual Learning
- Blog: Few-Shot Continual Learning via Flat-to-Wide Approaches
- Blog: Cross-Domain Continual Learning for Edge Intelligence in Wireless ISAC Networks
- Blog: An Empirical Investigation of the Role of Pre-training in Lifelong Learning
- Blog: ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think
- Blog: SEAL: Searching Expandable Architectures for Incremental Learning
- Blog: Noise-based Selection of Robust Inherited Model for Accurate Continual Learning
- Blog: Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima
- Blog: STAR: Stability-Inducing Weight Perturbation for Continual Learning
- Blog: Representational Continuity for Unsupervised Continual Learning
- Blog: Efficient Bilevel Optimization for CKA-Guided MoE Upcycling
- Blog: Learning Bayesian Sparse Networks with Full Experience Replay for Continual Learning
- Blog: Make Continual Learning Stronger via C-Flat
- Blog: Artificial Neural Variability for Deep Learning: On Overfitting, Noise Memorization, and Catastrophic Forgetting
- Blog: Continual Adaptation of Visual Representations via Domain Randomization and Meta-Learning
- Blog: CoSCL: Cooperation of Small Continual Learners is Stronger Than a Big One
- Blog: Revisiting Catastrophic Forgetting in Large Language Model Tuning
- Blog: Toward Universal Medical Image Registration via Sharpness-Aware Meta-Continual Learning
- Blog: Understanding the Role of Training Regimes in Continual Learning
- Blog: Enhancing Robustness in Incremental Learning with Adversarial Training
- Blog: Unsupervised Few-Shot Continual Learning for Remote Sensing Image Scene Classification
- Blog: Task-aware Orthogonal Sparse Network for Exploring Shared Knowledge in Continual Learning
- Blog: Class-Incremental Continual Learning Into the eXtended DER-Verse
- Blog: Semi-supervised Drifted Stream Learning with Short Lookback
- Blog: Toward Universal Medical Image Registration via Sharpness-Aware Meta-Continual Learning
- Blog: Rethinking the Representational Continuity: Towards Unsupervised Continual Learning
- Blog: Improving Data-aware and Parameter-aware Robustness for Continual Learning
- Blog: A Survey on Few-Shot Class-Incremental Learning
- Blog: Create and Find Flatness: Building Flat Training Spaces in Advance for Continual Learning
- Blog: Doubly Perturbed Task-Free Continual Learning
- Blog: Data Augmented Flatness-aware Gradient Projection for Continual Learning
- Blog: Model Sensitivity Aware Continual Learning
- Blog: Make Continual Learning Stronger via C-Flat
- Blog: Deep learning via message passing algorithms based on belief propagation
- Blog: Lookbehind-SAM: k steps back, 1 step forward
- Blog: C-Flat++: Towards a More Efficient and Powerful Framework for Continual Learning
- Blog: Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond
- Blog: Few-Shot Continual Learning via Flat-to-Wide Approaches
- Blog: Towards guarantees for parameter isolation in continual learning
- Blog: Linear Mode Connectivity in Multitask and Continual Learning
- Blog: Continuous Coordination As a Realistic Scenario for Lifelong Learning
- Blog: Natural continual learning: success is a journey, not (just) a destination
- Blog: Towards Plastic and Stable Exemplar-Free Incremental Learning: A Dual-Learner Framework with Cumulative Parameter Averaging
- Blog: Advancing Prompt-Based Methods for Replay-Independent General Continual Learning
- Blog: Mitigating Parameter Interference in Model Merging via Sharpness-Aware Fine-Tuning
Showing 60 of 81 papers.
History & citation
Current · Permanent link
- Flat Minima for Robust Continual Learning and Model Merging merged into this direction (60% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_loss_landscape_flattening_flat_minima_op_51d690ba,
title = {loss landscape flattening (flat minima optimization)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/loss-landscape-flattening-flat-minima-optimization/rdr_51d690bab6e941c796d9c0c955f29eb9},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 2, frozen text):
@misc{lacuna_loss_landscape_flattening_flat_minima_op_51d690ba_v2,
title = {loss landscape flattening (flat minima optimization)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/loss-landscape-flattening-flat-minima-optimization/rdr_51d690bab6e941c796d9c0c955f29eb9/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-21},
}