Image de couverture de livre

Making Robust Generalizers Less Rigid with Loss Concentration

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Holland, Matthew J., Hamada, Toma
Format:	Preprint
Publié:	2024
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

Criterion Collapse and Loss Distribution Control
par: Holland, Matthew J.
Publié: (2024)

Robust variance-regularized risk minimization with concomitant scaling
par: Holland, Matthew J.
Publié: (2023)

Generating Less Certain Adversarial Examples Improves Robust Generalization
par: Zhang, Minxing, et autres
Publié: (2023)

Does Training on Synthetic Data Make Models Less Robust?
par: Zhang, Lingze, et autres
Publié: (2025)

Can Learned Optimization Make Reinforcement Learning Less Difficult?
par: Goldie, Alexander David, et autres
Publié: (2024)

Soft ascent-descent as a stable and flexible alternative to flooding
par: Holland, Matthew J., et autres
Publié: (2023)

Are Compressed Language Models Less Subgroup Robust?
par: Gee, Leonidas, et autres
Publié: (2024)

Wait-Less Offline Tuning and Re-solving for Online Decision Making
par: Sun, Jingruo, et autres
Publié: (2024)

Learning Displacement-Robust Representations for Landslide Early Warning under Rainfall Forecast Uncertainty
par: Ozeki, Ren, et autres
Publié: (2026)

Gen-DFL: Decision-Focused Generative Learning for Robust Decision Making
par: Wang, Prince Zizhuang, et autres
Publié: (2025)

Taking the Road Less Scheduled with Adaptive Polyak Steps
par: Oikonomou, Dimitris, et autres
Publié: (2025)

Towards Poisoning Robustness Certification for Natural Language Generation
par: Ghitu, Mihnea, et autres
Publié: (2026)

Making AI Less "Thirsty": Uncovering and Addressing the Secret Water Footprint of AI Models
par: Li, Pengfei, et autres
Publié: (2023)

Offline Decision Transformers for Neural Combinatorial Optimization: Surpassing Heuristics on the Traveling Salesman Problem
par: Ohigashi, Hironori, et autres
Publié: (2026)

Lower Bounds on Adversarial Robustness for Multiclass Classification with General Loss Functions
par: Trillos, Camilo Andrés García, et autres
Publié: (2025)

Novel Actor-Critic Algorithm for Robust Decision Making of CAV under Delays and Loss of V2X Data
par: Kherroubi, Zine el abidine
Publié: (2024)

Oscillations Make Neural Networks Robust to Quantization
par: Wenshøj, Jonathan, et autres
Publié: (2025)

Loss Landscape Geometry and the Learning of Symmetries: Or, What Influence Functions Reveal About Robust Generalization
par: Amarel, James, et autres
Publié: (2026)

RobustNeRF: Ignoring Distractors with Robust Losses
par: Sabour, Sara, et autres
Publié: (2023)

Pay Less Attention to Function Words for Free Robustness of Vision-Language Models
par: Tian, Qiwei, et autres
Publié: (2025)

Robust Losses for Decision-Focused Learning
par: Schutte, Noah, et autres
Publié: (2023)

Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable
par: Huang, Tiansheng, et autres
Publié: (2025)

Towards Calibrated Losses for Adversarial Robust Reject Option Classification
par: Shah, Vrund, et autres
Publié: (2024)

On the Robustness of Kernel Ridge Regression Using the Cauchy Loss Function
par: Wen, Hongwei, et autres
Publié: (2025)

Introducing Fractional Classification Loss for Robust Learning with Noisy Labels
par: Kurucu, Mert Can, et autres
Publié: (2025)

Robust Loss Functions for Training Decision Trees with Noisy Labels
par: Wilton, Jonathan, et autres
Publié: (2023)

MVG-CRPS: A Robust Loss Function for Multivariate Probabilistic Forecasting
par: Zheng, Vincent Zhihao, et autres
Publié: (2024)

Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less Risky
par: Hathidara, Ashutosh, et autres
Publié: (2025)

Robust Amortized Bayesian Inference with Self-Consistency Losses on Unlabeled Data
par: Mishra, Aayush, et autres
Publié: (2025)

3D Molecule Generation from Rigid Motifs via SE(3) Flows
par: Poletukhin, Roman, et autres
Publié: (2026)

Less-to-More Generalization: Unlocking More Controllability by In-Context Generation
par: Wu, Shaojin, et autres
Publié: (2025)

LoRA Learns Less and Forgets Less
par: Biderman, Dan, et autres
Publié: (2024)

A Unifying Generator Loss Function for Generative Adversarial Networks
par: Veiner, Justin, et autres
Publié: (2023)

Two-stage LLM Fine-tuning with Less Specialization and More Generalization
par: Wang, Yihan, et autres
Publié: (2022)

Advancing Supervised Learning with the Wave Loss Function: A Robust and Smooth Approach
par: Akhtar, Mushir, et autres
Publié: (2024)

HawkEye: Advancing Robust Regression with Bounded, Smooth, and Insensitive Loss Function
par: Akhtar, Mushir, et autres
Publié: (2024)

Loss Functions and Operators Generated by f-Divergences
par: Roulet, Vincent, et autres
Publié: (2025)

An Inclusive Theoretical Framework of Robust Supervised Contrastive Loss against Label Noise
par: Cui, Jingyi, et autres
Publié: (2025)

Designing a Robust, Bounded, and Smooth Loss Function for Improved Supervised Learning
par: Mahato, Soumi, et autres
Publié: (2026)

A Weighted Loss Approach to Robust Federated Learning under Data Heterogeneity
par: Erbani, Johan, et autres
Publié: (2025)