AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
Category
2,616 papers
It is argued that ARD endures because of its seamless integration with kernel learning, universal software support, and low cost, and it is argued that ARD delivers effective rather than exact sparsity.
It is shown that a studentized multiplier bootstrap of the GP derivative process repairs both its validity through an invariance principle for quadratic forms, and it is shown that asymptotic family-wise and false-discovery-rate control across inputs are obtained.
Transformers have emerged as powerful architectures for learning solution operators of physical systems. Empirically the prediction error has been observed to decrease when the data size and model size increase, suggesting neural scaling behavior. Yet a theoretical understanding of such scaling laws for transformer-bas...
Conditional independence (CI) is a fundamental concept in statistics and machine learning. Recent advances in conditional generative modeling provide flexible tools for generative-model-based CI tests, which rely on an estimated conditional distribution to generate randomized samples. However, errors in estimating this...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Weighted split conformal prediction reweights calibration scores by the likelihood ratio between the test and training covariate distributions and guarantees marginal coverage under covariate shift. We study its coverage conditional on the calibration data. An elementary argument, based on a single concentration inequa...
It is found that multiple responses provide a qualitatively stronger benefit in this setting of generative systems, and is shown that a greedy multiplicative-weights learner achieving the upper bounds without any assumption on demonstrator quality is possible.
Finite-sample bounds are derived that separate the effects of critic estimation, neural drift regression, finite-sample SNIS, diffusion discretization, and inherited actor error on expected average policy suboptimality.
A convex combination of one-step and two-step residuals with a fixed mixing weight is considered to provide a natural bias--variance trade-off between approximation error under a restricted value-function class and the increased variance arising from multi-step importance weighting.
TabCon is developed, an amortized inference system built on a tabular foundation model that produces confidence intervals for new datasets through a simple forward pass, and offers considerably greater computational efficiency than the classical bootstrap procedure.
Retrieval-augmented generation (RAG) lets language models answer questions more accurately by consulting relevant documents. Many valuable collections, such as medical records, cannot be pooled because of privacy rules. Federated RAG leaves each collection with its owner, or node, which scores candidate answers from it...
We propose sliced Orlicz-Wasserstein (SOW) distance which is a generalization of sliced Wasserstein (SW) distance. SOW replaces the $L^p$ norm in SW with a Luxemburg norm cost induced by an Orlicz function $\phi$. First, we prove that SOW distance is a metric on the space of measures with finite Orlicz norm, and show t...
A doubly-anchored DRO framework whose ambiguity set is the intersection of $\phi$-divergence balls centered at the source law and a source-completed target reference law, the latter pairing the target covariate law with the source conditional law is introduced.
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.
