Copertina

Expert Routing with Synthetic Data for Continual Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Byun, Yewon, Mehta, Sanket Vaibhav, Garg, Saurabh, Strubell, Emma, Oberst, Michael, Wilder, Bryan, Lipton, Zachary C.
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Auditing Fairness under Unobserved Confounding
di: Byun, Yewon, et al.
Pubblicazione: (2024)

Valid Inference with Imperfect Synthetic Data
di: Byun, Yewon, et al.
Pubblicazione: (2025)

Decision-Focused Evaluation of Worst-Case Distribution Shift
di: Ren, Kevin, et al.
Pubblicazione: (2024)

Medical Adaptation of Large Language and Vision-Language Models: Are We Making Progress?
di: Jeong, Daniel P., et al.
Pubblicazione: (2024)

The Limited Impact of Medical Adaptation of Large Language and Vision-Language Models
di: Jeong, Daniel P., et al.
Pubblicazione: (2024)

No Free Lunch: Non-Asymptotic Analysis of Prediction-Powered Inference
di: Mani, Pranav, et al.
Pubblicazione: (2025)

Utility-Directed Conformal Prediction: A Decision-Aware Framework for Actionable Uncertainty Quantification
di: Cortes-Gomez, Santiago, et al.
Pubblicazione: (2024)

Failure Modes of LLMs for Causal Reasoning on Narratives
di: Yamin, Khurram, et al.
Pubblicazione: (2024)

Post-Hoc Reversal: Are We Selecting Models Prematurely?
di: Ranjan, Rishabh, et al.
Pubblicazione: (2024)

Leaving the Nest: Going Beyond Local Loss Functions for Predict-Then-Optimize
di: Shah, Sanket, et al.
Pubblicazione: (2023)

Online Data Collection for Efficient Semiparametric Inference
di: Gupta, Shantanu, et al.
Pubblicazione: (2024)

Learning treatment effects while treating those in need
di: Wilder, Bryan, et al.
Pubblicazione: (2024)

Contrastive Multiple Instance Learning for Weakly Supervised Person ReID
di: Tyo, Jacob, et al.
Pubblicazione: (2024)

RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold
di: Setlur, Amrith, et al.
Pubblicazione: (2024)

Power Hungry Processing: Watts Driving the Cost of AI Deployment?
di: Luccioni, Alexandra Sasha, et al.
Pubblicazione: (2023)

Comparing Targeting Strategies for Maximizing Social Welfare with Limited Resources
di: Sharma, Vibhhu, et al.
Pubblicazione: (2024)

Scaling Laws for Data Filtering -- Data Curation cannot be Compute Agnostic
di: Goyal, Sachin, et al.
Pubblicazione: (2024)

Fostering the Ecosystem of AI for Social Impact Requires Expanding and Strengthening Evaluation Standards
di: Wilder, Bryan, et al.
Pubblicazione: (2025)

Local Causal Discovery for Estimating Causal Effects
di: Gupta, Shantanu, et al.
Pubblicazione: (2023)

The Fragility of Fairness: Causal Sensitivity Analysis for Fair Machine Learning
di: Fawkes, Jake, et al.
Pubblicazione: (2024)

Revisiting Performance Claims for Chest X-Ray Models Using Clinical Context
di: Wang, Andrew, et al.
Pubblicazione: (2025)

Bayesian Neural Networks with Domain Knowledge Priors
di: Sam, Dylan, et al.
Pubblicazione: (2024)

IDIL: Imitation Learning of Intent-Driven Expert Behavior
di: Seo, Sangwon, et al.
Pubblicazione: (2024)

Opportunistic Expert Activation: Batch-Aware Expert Routing for Faster Decode Without Retraining
di: Oncescu, Costin-Andrei, et al.
Pubblicazione: (2025)

Explaining Concept Shift with Interpretable Feature Attribution
di: Lyu, Ruiqi, et al.
Pubblicazione: (2025)

Dependent Randomized Rounding for Budget Constrained Experimental Design
di: Yamin, Khurram, et al.
Pubblicazione: (2025)

OEUVRE: OnlinE Unbiased Variance-Reduced loss Estimation
di: Pardeshi, Kanad, et al.
Pubblicazione: (2025)

Combining digital data streams and epidemic networks for real time outbreak detection
di: Lyu, Ruiqi, et al.
Pubblicazione: (2025)

Distributionally Robust Feature Selection
di: Swaroop, Maitreyi, et al.
Pubblicazione: (2025)

Separation and Collaboration: Two-Level Routing Grouped Mixture-of-Experts for Multi-Domain Continual Learning
di: Zhou, Jialu, et al.
Pubblicazione: (2025)

Risk In Context: Benchmarking Privacy Leakage of Foundation Models in Synthetic Tabular Data Generation
di: Byun, Jessup, et al.
Pubblicazione: (2025)

The Impact of Differential Feature Under-reporting on Algorithmic Fairness
di: Akpinar, Nil-Jana, et al.
Pubblicazione: (2024)

On-device Streaming Discrete Speech Units
di: Choi, Kwanghee, et al.
Pubblicazione: (2025)

Beyond Surface-Level Similarity: Hierarchical Contamination Detection for Synthetic Training Data in Foundation Models
di: Mehta, Sushant
Pubblicazione: (2025)

Similarity-Aware Mixture-of-Experts for Data-Efficient Continual Learning
di: Mclaughlin, Connor, et al.
Pubblicazione: (2026)

Learning Treatment Effects during Resource Allocation via Priority-Queue Randomization
di: Lee, JungHo, et al.
Pubblicazione: (2026)

Normality-Guided Distributional Reinforcement Learning for Continuous Control
di: Byun, Ju-Seung, et al.
Pubblicazione: (2022)

Scaling Continual Learning to 300+ Tasks with Bi-Level Routing Mixture-of-Experts
di: Lou, Meng, et al.
Pubblicazione: (2026)

Can LLMs Reconcile Knowledge Conflicts in Counterfactual Reasoning
di: Yamin, Khurram, et al.
Pubblicazione: (2025)

Born Again Neural Networks
di: Furlanello, Tommaso, et al.
Pubblicazione: (2018)