Category
2,619 papers
Real-generation experiments that account for the pilot synchronization barrier show that HBN-async mitigates its overhead, helping translate statistical efficiency into practical evaluation benefits, and outperforming hindsight-tuned empirical and independent Bayesian baselines.
It is proved that task-predictive equivalence induces the unique minimal sufficient quotient $\mathcal{H}/\!\sim_\tau$, leaving active observability complexity strictly invariant while eliminating superfluous distinctions.
Overall, the results show that agents do not need to recompute action credit after every policy update: much of the historical evidence can be reused or cheaply corrected, reducing the additional interaction required to keep action decisions up to date.
A Graph-based Faithful sTep-level credit-assignment framework (GRAFT) that grafts all rollout trajectories into a trajectory graph, recovering node state-values via Bellman iteration on the graph, and assigning credit to each edge by the node value difference is proposed.
Reach audiences
Advertise in front of researchers, engineers, and readers.
**A field-level audit of one month of retraction deposits (v2)** Author: Trafalgar Law (independent). Data pulled from the public Crossref REST API on 2026-09-23. Sample and reproduction query included. This is a metadata audit, not an accusation against any publisher or author. ## Why On 2026-09-19 the record for a fi...
Simultaneous Latent Budget Trees, a probabilistic machine learning framework for classification trees in the presence of a stratification factor such as a temporal, spatial, or demographic variable, acting as a control variable or potential confounder, is introduced.
Probability-floor samplers substantially narrow the blind spot, demonstrating that the choice of truncation criterion matters for retaining human-used tokens and motivate decoding methods that preserve contextually appropriate low-probability choices while maintaining generation quality.
This work discretizes the spectral representation directly, preserving the correlation structure among spectral weights without requiring probability assumptions, and yields an efficient low-rank approximation that is positive semi-definite by construction and consistent under mild regularity conditions.
This article provides a unifying review of recent diffusion-based methods for generative lossy compression, with a focus on image compression, and highlights the role of common randomness and connections to inverse problems, and identifies open challenges.
This paper applies various NLP techniques to demonstrate feature de-biasing, feature compression, and industry classification in the commercial insurance context to show that NLP is not merely a supplementary tool but a foundational element of modern, data-driven insurance analytics.
A quantum reservoir processing framework that captures a broad range of physical computing models with quantum systems and it is numerically demonstrated that exponential concentration can still exist even with a physical reservoir such as an Ising model whenever the reservoir operates in a quantum-chaotic phase.
This paper develops theory for deep neural network (DNN) estimators under dependent data. To provide theory applicable to a variety of DNN-based estimators, I first establish nonasymptotic probability bounds on the theoretical and empirical $\mathcal{L}^{2}$-errors of nonparametric sieve estimators for a general class...
MIT Statistics and Data Science Center Director Alexander (Sasha) Rakhlin shares important considerations for departments and institutions.
By rethinking how large cloud computing systems operate, Associate Professor Christina Delimitrou seeks to make data centers more energy efficient.
As director, Bourg has focused on digital access, open and equitable scholarly publishing, and expanded support for data-intensive research.
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
Mobile Systems
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
