No article text was recorded for this version.
loss landscape flattening (flat minima generalization)
Version 1 of 1309 papers331 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Gradient Alignment for Cross-Domain Face Anti-Spoofing
- Blog: Flatness Improves Backbone Generalisation in Few-shot Classification
- Blog: Cross Domain Generative Augmentation: Domain Generalization with Latent Diffusion Models
- Blog: Sharpness & Shift-Aware Self-Supervised Learning
- Blog: Generalization of the Gibbs algorithm with high probability at low temperatures
- Blog: Visualizing and Understanding the Effectiveness of BERT
- Blog: Deep Mutual Learning
- Blog: Data-Efficient Double-Win Lottery Tickets from Robust Pre-training
- Blog: Semi-flat minima and saddle points by embedding neural networks to overparameterization
- Blog: Seeking Consistent Flat Minima for Better Domain Generalization via Refining Loss Landscapes
- Blog: Knowledge Distillation by On-the-Fly Native Ensemble
- Blog: A Flat Minima Perspective on Understanding Augmentations and Model Robustness
- Blog: A Flat Minima Perspective on Understanding Augmentations and Model Robustness
- Blog: Dense xUnit Networks
- Blog: Properties and Applications of Functions that Deep Learning Approximates
- Blog: Towards Binary-Valued Gates for Robust LSTM Training
- Blog: Local Superior Soups: A Catalyst for Model Merging in Cross-Silo Federated Learning
- Blog: Federated Domain Generalization with Generalization Adjustment
- Blog: SWAD: Domain Generalization by Seeking Flat Minima
- Blog: FedMR: Federated Learning via Model Recombination
- Blog: The Crucial Role of Normalization in Sharpness-Aware Minimization
- Blog: Flatness is Necessary, Neural Collapse is Not: Rethinking Generalization via Grokking
- Blog: Sharpness-Aware Model-Agnostic Long-Tailed Domain Generalization
- Blog: Sharpness-Aware Minimization in Genetic Programming
- Blog: FedSoL: Bridging Global Alignment and Local Generality in Federated Learning
- Blog: Leveraging Flatness to Improve Information-Theoretic Generalization Bounds for SGD
- Blog: A Flatter Loss for Bias Mitigation in Cross-dataset Facial Age Estimation
- Blog: A Closer Look at Smoothness in Domain Adversarial Training
- Blog: Annealing Self-Distillation Rectification Improves Adversarial Training
- Blog: Enhancing Generalization via Sharpness-Aware Trajectory Matching for Dataset Condensation
- Blog: Model Merging via Multi-Teacher Knowledge Distillation
- Blog: MedSeqFT: Sequential Fine-tuning Foundation Models for 3D Medical Image Segmentation
- Blog: Face Reconstruction Transfer Attack as Out-of-Distribution Generalization
- Blog: CoSCL: Cooperation of Small Continual Learners is Stronger Than a Big One
- Blog: Self-Distillation: Towards Efficient and Compact Neural Networks
- Blog: Apprentissage PAC-Bayésien sous le prisme de l’optimisation
- Blog: KoReA-SFL: Knowledge Replay-based Split Federated Learning Against Catastrophic Forgetting
- Blog: Diffusion-Guided Graph Data Augmentation
- Blog: Make Landscape Flatter in Differentially Private Federated Learning
- Blog: From Sharpness to Better Generalization for Speech Deepfake Detection
- Blog: Improving Generalization of Pre-trained Language Models via Stochastic Weight Averaging
- Blog: Sign-In to the Lottery: Reparameterizing Sparse Training From Scratch
- Blog: Improving Generalization of Pre-trained Language Models via Stochastic Weight Averaging
- Blog: Online Distilling from Checkpoints for Neural Machine Translation
- Blog: Fantastic Generalization Measures and Where to Find Them
- Blog: Seeking Consistent Flat Minima for Better Domain Generalization via Refining Loss Landscapes
- Blog: FedSoup: Improving Generalization and Personalization in Federated Learning via Selective Model Interpolation
- Blog: Efficient One Pass Self-distillation with Zipf's Label Smoothing
- Blog: Relatron: Automating Relational Machine Learning over Relational Databases
- Blog: FedCross: Towards Accurate Federated Learning via Multi-Model Cross Aggregation
- Blog: Consistent Sparse Deep Learning: Theory and Computation
- Blog: Transforming medical imaging with Transformers? A comparative review of key properties, current progresses, and future perspectives
- Blog: Adaptive Variance Reduction for Stochastic Optimization under Weaker Assumptions
- Blog: Self-Evolution Learning for Discriminative Language Model Pretraining
- Blog: Neural networks: from the perceptron to deep nets
- Blog: Effective Federated Adaptive Gradient Methods with Non-IID Decentralized Data
- Blog: Beyond Loss Functions: Exploring Data-Centric Approaches with Diffusion Model for Domain Generalization
- Blog: Sparse Task Vector Mixup with Hypernetworks for Efficient Knowledge Transfer in Whole-Slide Image Prognosis
- Blog: Averaging Weights Leads to Wider Optima and Better Generalization
- Blog: Generalization potential of large language models
Showing 60 of 309 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_loss_landscape_flattening_flat_minima_ge_4bb334d1,
title = {loss landscape flattening (flat minima generalization)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/loss-landscape-flattening-flat-minima-generalization/rdr_4bb334d1b10841fb9999b79415c8568d},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_loss_landscape_flattening_flat_minima_ge_4bb334d1_v1,
title = {loss landscape flattening (flat minima generalization)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/loss-landscape-flattening-flat-minima-generalization/rdr_4bb334d1b10841fb9999b79415c8568d/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}