Image de couverture de livre

There is a Singularity in the Loss Landscape

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Lowell, Mark
Format:	Preprint
Publié:	2022
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Landscaper: Understanding Loss Landscapes Through Multi-Dimensional Topological Analysis
par: Chen, Jiaqing, et autres
Publié: (2026)

Evaluating Loss Landscapes from a Topology Perspective
par: Xie, Tiankai, et autres
Publié: (2024)

Visualizing Loss Functions as Topological Landscape Profiles
par: Geniesse, Caleb, et autres
Publié: (2024)

Model Merging on Loss Landscape: A Geometry Perspective
par: Lu, Juanwu, et autres
Publié: (2026)

Early-Warning Signals of Grokking via Loss-Landscape Geometry
par: Xu, Yongzhong
Publié: (2026)

Matrix Sensing with Kernel Optimal Loss: Robustness and Optimization Landscape
par: Song, Xinyuan, et autres
Publié: (2025)

Identifying Sparsely Active Circuits Through Local Loss Landscape Decomposition
par: Chrisman, Brianna, et autres
Publié: (2025)

A Tale of Two Symmetries: Exploring the Loss Landscape of Equivariant Models
par: Xie, YuQing, et autres
Publié: (2025)

Practical Bayesian Inference for Speech SNNs: Uncertainty and Loss-Landscape Smoothing
par: Abdennadher, Yesmine, et autres
Publié: (2026)

Singular Vectors of Attention Heads Align with Features
par: Franco, Gabriel, et autres
Publié: (2026)

Loss Landscape Degeneracy and Stagewise Development in Transformers
par: Hoogland, Jesse, et autres
Publié: (2024)

Flat Channels to Infinity in Neural Loss Landscapes
par: Martinelli, Flavio, et autres
Publié: (2025)

Adapting Critic Match Loss Landscape Visualization to Off-policy Reinforcement Learning
par: Liu, Jingyi, et autres
Publié: (2026)

Loss Barcode: A Topological Measure of Escapability in Loss Landscapes
par: Barannikov, Serguei, et autres
Publié: (2020)

Visualizing Critic Match Loss Landscapes for Interpretation of Online Reinforcement Learning Control Algorithms
par: Liu, Jingyi, et autres
Publié: (2026)

A Loss Landscape Visualization Framework for Interpreting Reinforcement Learning: An ADHDP Case Study
par: Liu, Jingyi, et autres
Publié: (2026)

The Optimiser Hidden in Plain Sight: Training with the Loss Landscape's Induced Metric
par: Harvey, Thomas R.
Publié: (2025)

Probing Implicit Bias in Semi-gradient Q-learning: Visualizing the Effective Loss Landscapes via the Fokker--Planck Equation
par: Yin, Shuyu, et autres
Publié: (2024)

M-HOF-Opt: Multi-Objective Hierarchical Output Feedback Optimization via Multiplier Induced Loss Landscape Scheduling
par: Sun, Xudong, et autres
Publié: (2024)

A Unified Noise-Curvature View of Loss of Trainability
par: Baveja, Gunbir Singh, et autres
Publié: (2025)

PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models
par: Meng, Fanxu, et autres
Publié: (2024)

Fractal Landscapes in Policy Optimization
par: Wang, Tao, et autres
Publié: (2023)

Dispelling the Curse of Singularities in Neural Network Optimizations
par: Cao, Hengjie, et autres
Publié: (2026)

Enhancing Graph Classification Robustness with Singular Pooling
par: Ennadir, Sofiane, et autres
Publié: (2025)

Problematizing AI Omnipresence in Landscape Architecture
par: Fernberg, Phillip, et autres
Publié: (2024)

ANO : Faster is Better in Noisy Landscape
par: Kegreisz, Adrien
Publié: (2025)

A Generalized Singular Value Theory for Neural Networks
par: Brown, Brian Charles, et autres
Publié: (2026)

A Scalable Measure of Loss Landscape Curvature for Analyzing the Training Dynamics of LLMs
par: Kalra, Dayal Singh, et autres
Publié: (2026)

CP Loss: Channel-wise Perceptual Loss for Time Series Forecasting
par: Zha, Yaohua, et autres
Publié: (2026)

Singular Value Decomposition on Kronecker Adaptation for Large Language Model
par: Chong, Yee Hin, et autres
Publié: (2025)

Elliptic Loss Regularization
par: Hasan, Ali, et autres
Publié: (2025)

When Losses Align: Gradient-Based Composite Loss Weighting for Efficient Pretraining
par: Karpukhin, Ivan, et autres
Publié: (2026)

Robust Model-Based Optimization for Challenging Fitness Landscapes
par: Ghaffari, Saba, et autres
Publié: (2023)

Learning Advanced Self-Attention for Linear Transformers in the Singular Value Domain
par: Wi, Hyowon, et autres
Publié: (2025)

SPA-Cache: Singular Proxies for Adaptive Caching in Diffusion Language Models
par: Sun, Wenhao, et autres
Publié: (2026)

Investigating the Histogram Loss in Regression
par: Imani, Ehsan, et autres
Publié: (2024)

Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy
par: Shaik, Thanveer, et autres
Publié: (2023)

Exploring the Landscape for Generative Sequence Models for Specialized Data Synthesis
par: Zbeeb, Mohammad, et autres
Publié: (2024)

GADPN: Graph Adaptive Denoising and Perturbation Networks via Singular Value Decomposition
par: Deng, Hao, et autres
Publié: (2026)

FANoise: Singular Value-Adaptive Noise Modulation for Robust Multimodal Representation Learning
par: Li, Jiaoyang, et autres
Publié: (2025)