:: Library Catalog

Image de couverture de livre

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Singh, Sidak Pal, Mobahi, Hossein, Agarwala, Atish, Dauphin, Yann
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Computation and Language
Accès en ligne:	https://arxiv.org/abs/2502.02407
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Neglected Hessian component explains mysteries in Sharpness regularization
par: Dauphin, Yann N., et autres
Publié: (2024)

Hallmarks of Optimization Trajectories in Neural Networks: Directional Exploration and Redundancy
par: Singh, Sidak Pal, et autres
Publié: (2024)

Rethinking Attention: Exploring Shallow Feed-Forward Neural Networks as an Alternative to Attention Layers in Transformers
par: Bozic, Vukasin, et autres
Publié: (2023)

High dimensional theory of two-phase optimizers
par: Agarwala, Atish
Publié: (2026)

Per-example gradients: a new frontier for understanding and improving optimizers
par: Roulet, Vincent, et autres
Publié: (2025)

Introduction to speech recognition
par: Dauphin, Gabriel
Publié: (2024)

Accelerating Neural Network Training Along Sharp and Flat Directions
par: Zakarin, Daniyar, et autres
Publié: (2025)

Some Fundamental Aspects about Lipschitz Continuity of Neural Networks
par: Khromov, Grigory, et autres
Publié: (2023)

A density estimation perspective on learning from pairwise human preferences
par: Dumoulin, Vincent, et autres
Publié: (2023)

High dimensional analysis reveals conservative sharpening and a stochastic edge of stability
par: Agarwala, Atish, et autres
Publié: (2024)

Feature learning as alignment: a structural property of gradient descent in non-linear neural networks
par: Beaglehole, Daniel, et autres
Publié: (2024)

On the Interplay Between Stepsize Tuning and Progressive Sharpening
par: Roulet, Vincent, et autres
Publié: (2023)

What Does It Mean to Be a Transformer? Insights from a Theoretical Hessian Analysis
par: Ormaniec, Weronika, et autres
Publié: (2024)

Theoretical characterisation of the Gauss-Newton conditioning in Neural Networks
par: Zhao, Jim, et autres
Publié: (2024)

On the Foundations of Shortcut Learning
par: Hermann, Katherine L., et autres
Publié: (2023)

To Clip or not to Clip: the Dynamics of SGD with Gradient Clipping in High-Dimensions
par: Marshall, Noah, et autres
Publié: (2024)

What do near-optimal learning rate schedules look like?
par: Naganuma, Hiroki, et autres
Publié: (2026)

Exact Risk Curves of signSGD in High-Dimensions: Quantifying Preconditioning and Noise-Compression Effects
par: Xiao, Ke Liang, et autres
Publié: (2024)

Reasoning Boosts Opinion Alignment in LLMs
par: Berdoz, Frédéric, et autres
Publié: (2026)

Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning
par: Arefin, Md Rifat, et autres
Publié: (2024)

Towards Meta-Pruning via Optimal Transport
par: Theus, Alexander, et autres
Publié: (2024)

$Q\sharp$: Provably Optimal Distributional RL for LLM Post-Training
par: Zhou, Jin Peng, et autres
Publié: (2025)

Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks
par: Qiu, Shikai, et autres
Publié: (2025)

Mining Mental Health Signals: A Comparative Study of Four Machine Learning Methods for Depression Detection from Social Media Posts in Sorani Kurdish
par: Mohammed, Idrees, et autres
Publié: (2025)

Contextual Graph Transformer: A Small Language Model for Enhanced Engineering Document Information Extraction
par: Reddy, Karan, et autres
Publié: (2025)

Data-Aware Random Feature Kernel for Transformers
par: Farzam, Amirhossein, et autres
Publié: (2026)

Local vs Global continual learning
par: Lanzillotta, Giulia, et autres
Publié: (2024)

Agent-Omni: Test-Time Multimodal Reasoning via Model Coordination for Understanding Anything
par: Lin, Huawei, et autres
Publié: (2025)

KITE: Kernelized and Information Theoretic Exemplars for In-Context Learning
par: Singh, Vaibhav, et autres
Publié: (2025)

FEval-TTC: Fair Evaluation Protocol for Test-Time Compute
par: Rumiantsev, Pavel, et autres
Publié: (2025)

LLMs can learn self-restraint through iterative self-reflection
par: Piché, Alexandre, et autres
Publié: (2024)

Does Representation Matter? Exploring Intermediate Layers in Large Language Models
par: Skean, Oscar, et autres
Publié: (2024)

Exploring Precision and Recall to assess the quality and diversity of LLMs
par: Bronnec, Florian Le, et autres
Publié: (2024)

Robustmix: Improving Robustness by Regularizing the Frequency Bias of Deep Nets
par: Ngnawe, Jonas, et autres
Publié: (2023)

Stepping on the Edge: Curvature Aware Learning Rate Tuners
par: Roulet, Vincent, et autres
Publié: (2024)

A Gauge Theory of Superposition: Toward a Sheaf-Theoretic Atlas of Neural Representations
par: Javidnia, Hossein
Publié: (2026)

Semantic Sections: An Atlas-Native Feature Ontology for Obstructed Representation Spaces
par: Javidnia, Hossein
Publié: (2026)

Improving Direct Persian-English Speech-to-Speech Translation with Discrete Units and Synthetic Parallel Data
par: Rashidi, Sina, et autres
Publié: (2025)

A Comprehensive Approach to Misspelling Correction with BERT and Levenshtein Distance
par: Naziri, Amirreza, et autres
Publié: (2024)

Phases of Muon: When Muon Eclipses SignSGD
par: Paquette, Elliot, et autres
Publié: (2026)