Copertina

Lower bounds on transformers with infinite precision

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Kozachinskiy, Alexander
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

A completely uniform transformer for parity
di: Kozachinskiy, Alexander, et al.
Pubblicazione: (2025)

Optimal bounds for dissatisfaction in perpetual voting
di: Kozachinskiy, Alexander, et al.
Pubblicazione: (2024)

Simple online learning with consistent oracle
di: Kozachinskiy, Alexander, et al.
Pubblicazione: (2023)

Ehrenfeucht-Haussler Rank and Chain of Thought
di: Barceló, Pablo, et al.
Pubblicazione: (2025)

Parity, Sensitivity, and Transformers
di: Kozachinskiy, Alexander, et al.
Pubblicazione: (2026)

Explaining k-Nearest Neighbors: Abductive and Counterfactual Explanations
di: Barceló, Pablo, et al.
Pubblicazione: (2025)

Message Passing on the Edge: Towards Scalable and Expressive GNNs
di: Barceló, Pablo, et al.
Pubblicazione: (2025)

Continuity and Isolation Lead to Doubts or Dilemmas in Large Language Models
di: Pasten, Hector, et al.
Pubblicazione: (2025)

Language Generation: Complexity Barriers and Implications for Learning
di: Arenas, Marcelo, et al.
Pubblicazione: (2025)

Strassen Attention, Split VC Dimension and Compositionality in Transformers
di: Kozachinskiy, Alexander, et al.
Pubblicazione: (2025)

Estimation of Energy-dissipation Lower-bounds for Neuromorphic Learning-in-memory
di: Chen, Zihao, et al.
Pubblicazione: (2024)

Quantized Evolution Strategies: High-precision Fine-tuning of Quantized LLMs at Low-precision Cost
di: Xu, Yinggan, et al.
Pubblicazione: (2026)

Behaviour Policy Optimization: Provably Lower Variance Return Estimates for Off-Policy Reinforcement Learning
di: Goodall, Alexander W., et al.
Pubblicazione: (2025)

On the inductive bias of infinite-depth ResNets and the bottleneck rank
di: Boix-Adsera, Enric
Pubblicazione: (2025)

FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision
di: Shah, Jay, et al.
Pubblicazione: (2024)

LoKA: Low-precision Kernel Applications for Recommendation Models At Scale
di: Luo, Liang, et al.
Pubblicazione: (2026)

Upper Entropy for 2-Monotone Lower Probabilities
di: Vu, Tuan-Anh, et al.
Pubblicazione: (2026)

Carrying over algorithm in transformers
di: Kruthoff, Jorrit
Pubblicazione: (2024)

Tight Lower Bounds and Improved Convergence in Performative Prediction
di: Khorsandi, Pedram, et al.
Pubblicazione: (2024)

Variance-Dependent Regret Lower Bounds for Contextual Bandits
di: He, Jiafan, et al.
Pubblicazione: (2025)

Small transformer architectures for task switching
di: Gros, Claudius
Pubblicazione: (2025)

AgGym: An agricultural biotic stress simulation environment for ultra-precision management planning
di: Khosravi, Mahsa, et al.
Pubblicazione: (2024)

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design
di: Duanmu, Haojie, et al.
Pubblicazione: (2025)

Step-resolved data attribution for looped transformers
di: Kaissis, Georgios, et al.
Pubblicazione: (2026)

Weight-sparse transformers have interpretable circuits
di: Gao, Leo, et al.
Pubblicazione: (2025)

Upper and Lower Bounds for Distributionally Robust Off-Dynamics Reinforcement Learning
di: Liu, Zhishuai, et al.
Pubblicazione: (2024)

Model-based Offline Reinforcement Learning with Lower Expectile Q-Learning
di: Park, Kwanyoung, et al.
Pubblicazione: (2024)

Turbo Connection: Reasoning as Information Flow from Higher to Lower Layers
di: Tang, Mohan, et al.
Pubblicazione: (2026)

Learning the greatest common divisor: explaining transformer predictions
di: Charton, François
Pubblicazione: (2023)

Incorporating Domain Differential Equations into Graph Convolutional Networks to Lower Generalization Discrepancy
di: Sun, Yue, et al.
Pubblicazione: (2024)

Bitformer: An efficient Transformer with bitwise operation-based attention for Big Data Analytics at low-cost low-precision devices
di: Duan, Gaoxiang, et al.
Pubblicazione: (2023)

Beyond the Lower Bound: Bridging Regret Minimization and Best Arm Identification in Lexicographic Bandits
di: Xue, Bo, et al.
Pubblicazione: (2025)

Arnold: a generalist muscle transformer policy
di: Chiappa, Alberto Silvio, et al.
Pubblicazione: (2025)

Static and multivariate-temporal attentive fusion transformer for readmission risk prediction
di: Sun, Zhe, et al.
Pubblicazione: (2024)

Don't be lazy: CompleteP enables compute-efficient deep transformers
di: Dey, Nolan, et al.
Pubblicazione: (2025)

Financial time series augmentation using transformer based GAN architecture
di: Podobiński, Andrzej, et al.
Pubblicazione: (2026)

A Lower Bound for the Number of Linear Regions of Ternary ReLU Regression Neural Networks
di: Nakahara, Yuta, et al.
Pubblicazione: (2025)

Structural Positional Encoding for knowledge integration in transformer-based medical process monitoring
di: Irwin, Christopher, et al.
Pubblicazione: (2024)

$σ$-PCA: a building block for neural learning of identifiable linear transformations
di: Kanavati, Fahdi, et al.
Pubblicazione: (2023)

Decomposition-based multi-scale transformer framework for time series anomaly detection
di: Zhang, Wenxin, et al.
Pubblicazione: (2025)