Copertina

Celo2: Towards Learned Optimization Free Lunch

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Moudgil, Abhinav, Knyazev, Boris, Belilovsky, Eugene
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Celo: Training Versatile Learned Optimizers on a Compute Diet
di: Moudgil, Abhinav, et al.
Pubblicazione: (2025)

Accelerating Training with Neuron Interaction and Nowcasting Networks
di: Knyazev, Boris, et al.
Pubblicazione: (2024)

Meta-learning Optimizers for Communication-Efficient Learning
di: Joseph, Charles-Étienne, et al.
Pubblicazione: (2023)

PyLO: Towards Accessible Learned Optimizers in PyTorch
di: Janson, Paul, et al.
Pubblicazione: (2025)

Efficient Refusal Ablation in LLM through Optimal Transport
di: Nanfack, Geraldin, et al.
Pubblicazione: (2026)

Warming Up for Zeroth-Order Federated Pre-Training with Low Resource Clients
di: Legate, Gwen, et al.
Pubblicazione: (2025)

Not Only the Last-Layer Features for Spurious Correlations: All Layer Deep Feature Reweighting
di: Hameed, Humza Wajid, et al.
Pubblicazione: (2024)

No Free Lunch: Fundamental Limits of Learning Non-Hallucinating Generative Models
di: Wu, Changlong, et al.
Pubblicazione: (2024)

$μ$LO: Compute-Efficient Meta-Generalization of Learned Optimizers
di: Thérien, Benjamin, et al.
Pubblicazione: (2024)

(Almost) Free Modality Stitching of Foundation Models
di: Singh, Jaisidh, et al.
Pubblicazione: (2025)

No Free Lunch: Rethinking Internal Feedback for LLM Reasoning
di: Zhang, Yanzhi, et al.
Pubblicazione: (2025)

Less is More: Undertraining Experts Improves Model Upcycling
di: Horoi, Stefan, et al.
Pubblicazione: (2025)

Non-Uniform Parameter-Wise Model Merging
di: Camacho, Albert Manuel Orozco, et al.
Pubblicazione: (2024)

Model Parallelism With Subnetwork Data Parallelism
di: Singh, Vaibhav, et al.
Pubblicazione: (2025)

A Free Lunch in LLM Compression: Revisiting Retraining after Pruning
di: Wagner, Moritz, et al.
Pubblicazione: (2025)

DiffuMamba: High-Throughput Diffusion LMs with Mamba Backbone
di: Singh, Vaibhav, et al.
Pubblicazione: (2025)

Integer Scale: A Free Lunch for Faster Fine-grained Quantization of LLMs
di: Li, Qingyuan, et al.
Pubblicazione: (2024)

ACCO: Accumulate While You Communicate for Communication-Overlapped Sharded LLM Training
di: Nabli, Adel, et al.
Pubblicazione: (2024)

Separable Power of Classical and Quantum Learning Protocols Through the Lens of No-Free-Lunch Theorem
di: Wang, Xinbiao, et al.
Pubblicazione: (2024)

A No Free Lunch Theorem for Human-AI Collaboration
di: Peng, Kenny, et al.
Pubblicazione: (2024)

No-Free-Lunch Theories for Tensor-Network Machine Learning Models
di: Wu, Jing-Chuan, et al.
Pubblicazione: (2024)

FreeBind: Free Lunch in Unified Multimodal Space via Knowledge Fusion
di: Wang, Zehan, et al.
Pubblicazione: (2024)

Graph Neural Networks for Learning Equivariant Representations of Neural Networks
di: Kofinas, Miltiadis, et al.
Pubblicazione: (2024)

Harmony in Diversity: Merging Neural Networks with Canonical Correlation Analysis
di: Horoi, Stefan, et al.
Pubblicazione: (2024)

Free Lunch in Medical Image Foundation Model Pre-training via Randomized Synthesis and Disentanglement
di: Wei, Yuhan, et al.
Pubblicazione: (2026)

CoPE: Clipped RoPE as A Scalable Free Lunch for Long Context LLMs
di: Li, Haoran, et al.
Pubblicazione: (2026)

Free Lunch for Federated Remote Sensing Target Fine-Grained Classification: A Parameter-Efficient Framework
di: Chen, Shengchao, et al.
Pubblicazione: (2024)

Preference Conditioned Multi-Objective Reinforcement Learning: Decomposed, Diversity-Driven Policy Optimization
di: Ambadkar, Tanmay, et al.
Pubblicazione: (2026)

LLMInit: A Free Lunch from Large Language Models for Selective Initialization of Recommendation
di: Zhang, Weizhi, et al.
Pubblicazione: (2025)

RL$^3$: Boosting Meta Reinforcement Learning via RL inside RL$^2$
di: Bhatia, Abhinav, et al.
Pubblicazione: (2023)

Towards General-Purpose Model-Free Reinforcement Learning
di: Fujimoto, Scott, et al.
Pubblicazione: (2025)

VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters
di: Chen, Mouxiang, et al.
Pubblicazione: (2024)

Simple and Scalable Strategies to Continually Pre-train Large Language Models
di: Ibrahim, Adam, et al.
Pubblicazione: (2024)

Towards Understanding the Optimization Mechanisms in Deep Learning
di: Qi, Binchuan, et al.
Pubblicazione: (2025)

REAM: Merging Improves Pruning of Experts in LLMs
di: Jha, Saurav, et al.
Pubblicazione: (2026)

Evolutionary Policy Optimization
di: Wang, Jianren, et al.
Pubblicazione: (2025)

Solver-Free Decision-Focused Learning for Linear Optimization Problems
di: Berden, Senne, et al.
Pubblicazione: (2025)

Towards Operationalizing Right to Data Protection
di: Java, Abhinav, et al.
Pubblicazione: (2024)

Feedback Lunch: Learned Feedback Codes for Secure Communications
di: Zhou, Yingyao, et al.
Pubblicazione: (2025)

One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt
di: Liu, Tao, et al.
Pubblicazione: (2025)