A loss-driven Bayesian active learning framework derives unique acquisition objectives from arbitrary losses, with analytic solutions available when the loss is a weighted Bregman divergence.
[Yes] (b) An analysis of the properties and complexity (time, space, sample size) of any algorithm
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 7roles
background 1polarities
background 1representative citing papers
Defining the Rashomon set for dimension reduction enables interpretable, robust visualizations by aligning embeddings with known structure and extracting consistent local relationships across multiple good embeddings.
A generalization bound based on a new feature-label distortion concept guides optimization of feature alignment versus target fitting in cross-modal adaptation and yields better empirical performance.
ARB dynamically prioritizes replay buffer samples by on-policyness to balance stability and performance in offline-to-online RL.
AdaScale-TuRBO scales Gaussian process lengthscales with problem dimension D and trust region side length L to preserve kernel geometry and improve performance over standard TuRBO in high-dimensional settings.
DIVERSED relaxes the verification step in speculative decoding with a dynamic ensemble verifier to raise token acceptance rates and speed up inference while keeping output quality intact.
Optimizing a single scalar temperature improves semantic calibration, discrimination, and entropy in language model question-answering over heuristic baselines and token-level recalibration methods.
citing papers explorer
-
Loss-Driven Bayesian Active Learning
A loss-driven Bayesian active learning framework derives unique acquisition objectives from arbitrary losses, with analytic solutions available when the loss is a weighted Bregman divergence.
-
The Rashomon Effect for Visualizing High-Dimensional Data
Defining the Rashomon set for dimension reduction enables interpretable, robust visualizations by aligning embeddings with known structure and extracting consistent local relationships across multiple good embeddings.
-
Rethinking Cross-Modal Fine-Tuning: Optimizing the Interaction Between Feature Alignment and Target Fitting
A generalization bound based on a new feature-label distortion concept guides optimization of feature alignment versus target fitting in cross-modal adaptation and yields better empirical performance.
-
Adaptive Replay Buffer for Offline-to-Online Reinforcement Learning
ARB dynamically prioritizes replay buffer samples by on-policyness to balance stability and performance in offline-to-online RL.
-
Rethinking Trust Region Bayesian Optimization in High Dimensions
AdaScale-TuRBO scales Gaussian process lengthscales with problem dimension D and trust region side length L to preserve kernel geometry and improve performance over standard TuRBO in high-dimensional settings.
-
DIVERSED: Relaxed Speculative Decoding via Dynamic Ensemble Verification
DIVERSED relaxes the verification step in speculative decoding with a dynamic ensemble verifier to raise token acceptance rates and speed up inference while keeping output quality intact.
-
Improving Semantic Uncertainty Quantification in Language Model Question-Answering via Token-Level Temperature Scaling
Optimizing a single scalar temperature improves semantic calibration, discrimination, and entropy in language model question-answering over heuristic baselines and token-level recalibration methods.