Copertina

On the Diminishing Returns of Width for Continual Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Guha, Etash, Lakshman, Vihan
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

Exploring and Applying Audio-Based Sentiment Analysis in Music
di: Jhanji, Etash
Pubblicazione: (2024)

Solving Robust MDPs through No-Regret Dynamics
di: Guha, Etash Kumar
Pubblicazione: (2023)

Technical Debt in In-Context Learning: Diminishing Efficiency in Long Context
di: Joo, Taejong, et al.
Pubblicazione: (2025)

Archon: An Architecture Search Framework for Inference-Time Techniques
di: Saad-Falcon, Jon, et al.
Pubblicazione: (2024)

CLoVE: Personalized Federated Learning through Clustering of Loss Vector Embeddings
di: Bhatia, Randeep, et al.
Pubblicazione: (2025)

Virtual Width Networks
di: Seed, et al.
Pubblicazione: (2025)

Down with the Hierarchy: The 'H' in HNSW Stands for "Hubs"
di: Munyampirwa, Blaise, et al.
Pubblicazione: (2024)

Adaptive Width Neural Networks
di: Errica, Federico, et al.
Pubblicazione: (2025)

Imitation Learning as Return Distribution Matching
di: Lazzati, Filippo, et al.
Pubblicazione: (2025)

On the Surprising Effectiveness of Large Learning Rates under Standard Width Scaling
di: Haas, Moritz, et al.
Pubblicazione: (2025)

Meta-Learning Reinforcement Learning for Crypto-Return Prediction
di: Wang, Junqiao, et al.
Pubblicazione: (2025)

Return-to-Go Is More Than a Number: Q-Guided Alignment for Return-Conditioned Supervised Learning
di: Yang, Yuxiao, et al.
Pubblicazione: (2026)

Infinite Width Models That Work: Why Feature Learning Doesn't Matter as Much as You Think
di: Sernau, Luke
Pubblicazione: (2024)

Mixture of Universal Experts: Scaling Virtual Width via Depth-Width Transformation
di: Chen, Yilong, et al.
Pubblicazione: (2026)

Lightweight LSTM Model for Energy Theft Detection via Input Data Reduction
di: Collier, Caylum, et al.
Pubblicazione: (2025)

PANDA: Expanded Width-Aware Message Passing Beyond Rewiring
di: Choi, Jeongwhan, et al.
Pubblicazione: (2024)

AdaQAT: Adaptive Bit-Width Quantization-Aware Training
di: Gernigon, Cédric, et al.
Pubblicazione: (2024)

Outliers and Calibration Sets have Diminishing Effect on Quantization of Modern LLMs
di: Paglieri, Davide, et al.
Pubblicazione: (2024)

In-Dataset Trajectory Return Regularization for Offline Preference-based Reinforcement Learning
di: Tu, Songjun, et al.
Pubblicazione: (2024)

STAS: Spatial-Temporal Return Decomposition for Multi-agent Reinforcement Learning
di: Chen, Sirui, et al.
Pubblicazione: (2023)

Deep Edge Filter: Return of the Human-Crafted Layer in Deep Learning
di: Lee, Dongkwan, et al.
Pubblicazione: (2025)

Completed Hyperparameter Transfer across Modules, Width, Depth, Batch and Duration
di: Mlodozeniec, Bruno, et al.
Pubblicazione: (2025)

The WidthWall: A Strict Expressivity Hierarchy for Hypergraph Neural Networks
di: Jiang, Fengqing, et al.
Pubblicazione: (2026)

How to Provably Improve Return Conditioned Supervised Learning?
di: Liu, Zhishuai, et al.
Pubblicazione: (2025)

Diminishing Stereotype Bias in Image Generation Model using Reinforcemenlent Learning Feedback
di: Chen, Xin, et al.
Pubblicazione: (2024)

PROTOCOL: Late Interaction Retrieval for Protein Homolog Search
di: Cohn, Gabrielle, et al.
Pubblicazione: (2026)

Polynomial Threshold Functions of Bounded Tree-Width: Some Explainability and Complexity Aspects
di: Chubarian, Karine, et al.
Pubblicazione: (2025)

NNiT: Width-Agnostic Neural Network Generation with Structurally Aligned Weight Spaces
di: Kim, Jiwoo, et al.
Pubblicazione: (2026)

Return Augmented Decision Transformer for Off-Dynamics Reinforcement Learning
di: Wang, Ruhan, et al.
Pubblicazione: (2024)

Beyond Expected Return: Accounting for Policy Reproducibility when Evaluating Reinforcement Learning Algorithms
di: Flageat, Manon, et al.
Pubblicazione: (2023)

The Return of Pseudosciences in Artificial Intelligence: Have Machine Learning and Deep Learning Forgotten Lessons from Statistics and History?
di: Sublime, Jérémie
Pubblicazione: (2024)

The Graphon Limit Hypothesis: Understanding Neural Network Pruning via Infinite Width Analysis
di: Pham, Hoang, et al.
Pubblicazione: (2025)

Geometric Limits of Knowledge Distillation: A Minimum-Width Theorem via Superposition Theory
di: Sarkar, Nilesh, 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)

Multi-objective Reinforcement Learning with Nonlinear Preferences: Provable Approximation for Maximizing Expected Scalarized Return
di: Peng, Nianli, et al.
Pubblicazione: (2023)

Component Based Quantum Machine Learning Explainability
di: White, Barra, et al.
Pubblicazione: (2025)

SACn: Soft Actor-Critic with n-step Returns
di: Łyskawa, Jakub, et al.
Pubblicazione: (2025)

Breaking the Curse of Dimensionality: On the Stability of Modern Vector Retrieval
di: Lakshman, Vihan, et al.
Pubblicazione: (2025)

The Median is Easier than it Looks: Approximation with a Constant-Depth, Linear-Width ReLU Network
di: Dutta, Abhigyan, et al.
Pubblicazione: (2026)

Expected Return Causes Outcome-Level Mode Collapse in Reinforcement Learning and How to Fix It with Inverse Probability Scaling
di: Sinha, Abhijeet, et al.
Pubblicazione: (2026)