Copertina

Simmering: Sufficient is better than optimal for training neural networks

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Babayan, Irina, Aliahmadi, Hazhir, van Anders, Greg
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Entropic Auto-Encoding via Implicit Free-Energy Minimization
di: Aliahmadi, Hazhir, et al.
Pubblicazione: (2026)

Flashpoints Signal Hidden Inherent Instabilities in Land-Use Planning
di: Aliahmadi, Hazhir, et al.
Pubblicazione: (2023)

Adaptive multiple optimal learning factors for neural network training
di: Challagundla, Jeshwanth
Pubblicazione: (2024)

Transforming Design Spaces Using Pareto-Laplace Filters
di: Aliahmadi, Hazhir, et al.
Pubblicazione: (2024)

Filters reveal emergent structure in computational morphogenesis
di: Aliahmadi, Hazhir, et al.
Pubblicazione: (2025)

When narrower is better: the narrow width limit of Bayesian parallel branching neural networks
di: Zhang, Zechen, et al.
Pubblicazione: (2024)

Confidence-gated training for efficient early-exit neural networks
di: Mokssit, Saad, et al.
Pubblicazione: (2025)

A comparative analysis of a neural network with calculated weights and a neural network with random generation of weights based on the training dataset size
di: Geidarov, Polad
Pubblicazione: (2025)

Language models are better than humans at next-token prediction
di: Shlegeris, Buck, et al.
Pubblicazione: (2022)

Do graph neural network states contain graph properties?
di: Pelletreau-Duris, Tom, et al.
Pubblicazione: (2024)

Target noise: A pre-training based neural network initialization for efficient high resolution learning
di: Wang, Shaowen, et al.
Pubblicazione: (2026)

On permutation-invariant neural networks
di: Kimura, Masanari, et al.
Pubblicazione: (2024)

Sobolev acceleration for neural networks
di: Oh, Jong Kwon, et al.
Pubblicazione: (2025)

Attention mechanisms in neural networks
di: Hays, Hasi
Pubblicazione: (2026)

An algorithmic framework for the optimization of deep neural networks architectures and hyperparameters
di: Keisler, Julie, et al.
Pubblicazione: (2023)

Two are better than one: Context window extension with multi-grained self-injection
di: Han, Wei, et al.
Pubblicazione: (2024)

Efficient and provably convergent end-to-end training of deep neural networks with linear constraints
di: Yang, Zonglin, et al.
Pubblicazione: (2026)

Mechanistic origins of catastrophic forgetting: why RL preserves circuits better than SFT?
di: Nunez, Jeanmely Rojas, et al.
Pubblicazione: (2026)

Action-Sufficient Goal Representations
di: Hyeon, Jinu, et al.
Pubblicazione: (2026)

Principles of Lipschitz continuity in neural networks
di: Luo, Róisín
Pubblicazione: (2026)

Linearity-based neural network compression
di: Dobler, Silas, et al.
Pubblicazione: (2025)

Astral: training physics-informed neural networks with error majorants
di: Fanaskov, Vladimir, et al.
Pubblicazione: (2024)

Search-contempt: a hybrid MCTS algorithm for training AlphaZero-like engines with better computational efficiency
di: Joshi, Ameya
Pubblicazione: (2025)

A framework for measuring the training efficiency of a neural architecture
di: Cueto-Mendoza, Eduardo, et al.
Pubblicazione: (2024)

Towards graph neural networks for provably solving convex optimization problems
di: Qian, Chendi, et al.
Pubblicazione: (2025)

Applying graph neural network to SupplyGraph for supply chain network
di: Han, Kihwan
Pubblicazione: (2024)

Sufficient Invariant Learning for Distribution Shift
di: Kim, Taero, et al.
Pubblicazione: (2022)

Understanding the dynamics of the frequency bias in neural networks
di: Molina, Juan, et al.
Pubblicazione: (2024)

Graph neural networks informed locally by thermodynamics
di: Tierz, Alicia, et al.
Pubblicazione: (2024)

Graph neural networks and non-commuting operators
di: Velasco, Mauricio, et al.
Pubblicazione: (2024)

LayerCollapse: Adaptive compression of neural networks
di: Shabgahi, Soheil Zibakhsh, et al.
Pubblicazione: (2023)

Self-Improving Pretraining: using post-trained models to pretrain better models
di: Tan, Ellen Xiaoqing, et al.
Pubblicazione: (2026)

Outlier-robust neural network training: variation regularization meets trimmed loss to prevent functional breakdown
di: Okuno, Akifumi, et al.
Pubblicazione: (2023)

Crystal structure prediction using graph neural combinatorial optimization
di: Gerolymatos, Stavros, et al.
Pubblicazione: (2026)

Sufficient and Necessary Explanations (and What Lies in Between)
di: Bharti, Beepul, et al.
Pubblicazione: (2024)

Randomness and signal propagation in physics-informed neural networks (PINNs): A neural PDE perspective
di: Tucny, Jean-Michel, et al.
Pubblicazione: (2025)

Planning in a recurrent neural network that plays Sokoban
di: Taufeeque, Mohammad, et al.
Pubblicazione: (2024)

Understanding polysemanticity in neural networks through coding theory
di: Marshall, Simon C., et al.
Pubblicazione: (2024)

Variational autoencoder-based neural network model compression
di: Cheng, Liang, et al.
Pubblicazione: (2024)

Conditional computation in neural networks: principles and research trends
di: Scardapane, Simone, et al.
Pubblicazione: (2024)