The paper introduces Entropic Projection Alignment (EPA), a unified framework that estimates, explains, and improves model performance under distribution shift by aligning source and target distributi…

This paper studies the behavior of mixture-of-experts (MoE) models under distribution shift and proposes an adversarial reweighting method to improve their calibration.

This survey analyzes the field of On-device Learning (ODL) for TinyML by categorizing existing works based on how they address various types of post-deployment distribution changes.

This paper proposes SHIFT, a topology-agnostic approach for communication-aware workload placement and routing optimization in large-scale heterogeneous systems, achieving up to 12.5x throughput impro…

The paper introduces SHIFT, a training-free attack that exploits the vulnerability of diffusion-based watermarking by stochastically deflecting the generative trajectory, achieving high removal rates…

A simple online algorithm is presented for the stacking problem to avoid shifts with a sufficient condition involving stacking area dimension, load/unload points, and maximum items.

The paper proposes Fair Fine-tuning (FFt), a method that fine-tunes a model using an Equalized Odds constraint on a complementary distribution, and theoretically proves that this approach significantl…

The paper proposes Fair Fine-tuning (FFt), a method that fine-tunes a model using an Equalized Odds constraint on a complementary distribution, and provides a formal theoretical bound linking this fai…

The paper analyzes the potential market impact of a large, unknown Bitcoin holder (the Satoshi overhang) and concludes that the mechanical downside risk is bounded, suggesting the terminal states are…

This paper introduces Distributional Random Forests, which replace mean-based CART splitting with criteria that compare full conditional response distributions in candidate children. The authors syste…

This paper studies distribution testing with respect to bounded classes of distinguishers, revealing connections between testable learning, verification of learning algorithms, and testing of structur…

The paper proposes DARTS, a distribution-aware active rollout trajectory shaping method that fundamentally accelerates LLM reinforcement learning by actively shaping the long-tail response distributio…

The paper introduces Temporary Power Adjusting Withholding (T-PAW), a generalized and more potent block withholding attack than the existing PAW attack, demonstrating that this attack can yield signif…

The paper models latent worker preferences in gig labor markets using the Preisach hysteresis model, demonstrating that predicting acceptance rates can simultaneously reduce labor costs and increase s…

The paper proposes a novel two-stage framework to differentially privatize tables of counts by focusing on preserving the accuracy of the underlying count distribution, introducing the specialized cyc…

This paper improves the theoretical bounds for estimating discrete probability distributions using the $\ell_\infty$ norm, resolving several open questions in the field.