Entropic Projection Alignment: Estimating, Explaining, and Improving Model Performance Under Distribution Shift
We propose a unified framework for addressing three key challenges of distribution shift: (1) estimating a model's performance on an unlabeled target domain, (2) explaining the shift by identifying the features responsible, and (3) improving the target domain performance. Our method, Entropic Projection Alignment (EPA), aligns the source distribution to the target by matching carefully selected moments while simultaneously minimising the KL divergence from the source. This formulation yields a u
Record details
Published: 29 May 2026
Source: arXiv
Category: Research
Topics: Safety & alignment
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
UF-AMA: A unified framework for cross-domain emotion recognition via adaptive multimodal alignment
arXiv · 29 May 2026
Subtitle-Aligned Fine-Tuning of Whisper for Swiss German ASR: Benchmark Contamination, Convention Mismatch, and an Honest Baseline at 25.6% WER (13.8% cWER)
arXiv · 29 May 2026
MyoSem: Aligning Electromyography to Natural-Language Action Semantics for Hand Action Understanding
arXiv · 29 May 2026
MIMO: Multilingual Information Retrieval via Monolingual Objectives
arXiv · 29 May 2026
DOA: Training-Free Decoder-Only Attention Policy for Long-Form Simultaneous Translation with SpeechLLMs
arXiv · 29 May 2026
Contribution Weights: A Geometrical Analysis of Self-Attention Transformers
arXiv · 29 May 2026
How to cite this record
ethics.ai (29 May 2026), “Entropic Projection Alignment: Estimating, Explaining, and Improving Model Performance Under Distribution Shift,” evidence record 3433, https://ethics.ai/record/3433 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.