Category
2,619 papers
This work introduces Coverage-Constrained Sequential Model Confidence Sets (CC-SMCS), which separate certifiably feasible, possibly feasible, and possibly constrained-optimal pipelines and establishes an impossibility result for safe certification at the coverage boundary.
Claims data can show that provider behavior changed but cannot by itself explain why. Fraud, waste, and abuse (FWA) review requires identifying material behavior, locating the codes and dollars driving it, and testing plausible explanations. Forecast residuals conflate growth, service-line shifts, code maintenance, and...
A learner's current observations need not determine its response to further training. We formulate intrinsic-extrinsic coupling through the continuation-conditioned value of a constrained learning-state intervention, with observation-relative fibers describing present agreement. An executable finite-frame classifier-he...
A released table is often treated as an i.i.d. sample, although its repeated rows may encode business frequency, repeated entities, joins, resampling, or extraction errors. We show that this ambiguity creates a hidden measurement layer with three consequences: feature-identical rows impose an attained evaluation ceilin...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Validating a model on a time series asks for three things at once: each training run should use most of the sample (sufficiency), the test sets should together cover most of the sample (coverage), and training data should come before test data (causality). We prove that the three cannot be had together and price each o...
This work develops a novel sampling algorithm, Neural Transport Nested Sampling (NTNS), which combines the classical strengths of nested sampling with modern neural flow-based methods, and is the first neural sampler to return a calibrated, temperature resolved partition function estimate at this scale.
This work maps entropy-regularized RLVR over myopic tabular policies onto an energy-based (spin-glass) model over deterministic policies, and finds that a transformer trained from scratch, using only last-token rewards, successfully learns an algorithmic chain of thought for iterated non-Abelian group multiplications.
Semi-supervised anomaly detection, which aims to improve the anomaly detection performance by using a small amount of labeled anomaly data in addition to unlabeled data, has attracted attention. Existing semi-supervised approaches assume that most unlabeled data are normal, and train anomaly detectors by minimizing the...
Direct Message Approximation (DMA), which approximates factor-to-variable messages directly rather than the marginal, is introduced and a master theorem (proper messages, any graph) bounding marginal KL from message KL is proved, with three structural corollaries.
FB-GDM is robust when the forward operator, the noise level, or the image distribution changes, and stays close to a per-problem $\Pi$GDM oracle throughout and does not exhibit the hallucinations observed with DPS, whereas DPS substantially degrades at a fixed scale and $\Pi$GDM stays competitive only if it is re-tuned...
Large language models can interpret natural lan- guage, yet robust decisions remain challenging. Jev-like models expose structured choices, but these interfaces do not directly provide numeri- cal values at a requested precision. We propose NUMERICJEV, a training-free numerical decod- ing algorithm that enables numeric...
The proposed SGA first characterizes the topology of all potential forecast branches using a directed acyclic graph, such that the graph complexity bounds the uncertainty of multi-step TSFM forecasts, and then precisely measures the graph complexity by integrating both topological information and TSFM-inherent stochast...
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.
