arXiv AI
Complementary Feature Domains: Information Preservation Does Not Imply Predictive-Contribution Preservation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Oct 9
Refinement as a Service: Algorithmic Predictor Refinement
The paper investigates how to combine multiple calibrated predictors into a single refined predictor that preserves all available information and cannot be further refined. It models calibrated predictors as signaling schemes and defines refinement via feature‑independent garblings, showing that a new predictor is constructible exactly when its signal vector lies in the linear span of the input signal vectors. The authors provide algorithmic results: deterministic refinement is polynomial‑time solvable for two predictors but NP‑hard for many, while randomized refinement admits a polynomial‑time algorithm for any number of inputs by decomposing signal vectors into extreme rays of a polyhedral cone.
arXiv Machine Learning
Jul 22
Breaking Feedback-Blindness: Utility-Augmented Transformer for Sequential Decision Making
arXiv:2607. 18910v1 Announce Type: new Abstract: Sequential decision making in non-stationary and partially observable environments requires rapid adaptation to latent regime changes.
arXiv Machine Learning
Jun 30
Predictive Objectives Discard Exogenous Control-Relevant Features: A Controlled Mechanistic Study
arXiv:2606. 30068v1 Announce Type: new Abstract: Joint-embedding predictive (JEPA-style) objectives learn representations by predicting future latents.
arXiv AI
4d ago
Predictive Closure: A Set-Level Characterization of JEPA's Feature Selection
arXiv:2610.27364v1 Announce Type: cross Abstract: In joint-embedding predictive architectures (JEPA), an encoder and a predictor are trained together to produce a representation that minimizes the er...
arXiv Machine Learning
Jun 30
Decision-Value Attribution in Predict-then-Optimize Systems
arXiv:2606. 29878v1 Announce Type: new Abstract: Predictive models are increasingly embedded in operational decision-making, yet standard explanation methods typically explain forecasts rather than the decisions those forecasts induce.
arXiv Machine Learning
Jun 18
Decomposing Prediction Mechanisms for In-Context Recall
arXiv:2507. 01414v2 Announce Type: replace Abstract: We introduce a new family of toy problems that combine features of linear-regression-style continuous in-context learning (ICL) with discrete associative recall.