Category
2,653 papers
It is proved that the constrained decoupled objective is equivalent at optimality to a specific joint penalty on the inner and outer weights, for any positively homogeneous activation, and thus admits a clean projected and proximal formulation.
Frontier language models now produce professional deliverables that expert graders judge to match human work on a substantial share of economically valuable tasks, yet most enterprise GenAI initiatives fail to show a measurable business effect and a large fraction of agentic projects are expected to be cancelled. We ar...
The existence-field diffusion model (EFDM), which associates each potential point with a continuous variable representing its degree of presence, is proposed, which uses Gaussian diffusion to jointly model point locations and cardinality through a simple continuous representation.
PBL is more effective for students with low BSPS, whereas Discovery Learning is more effective for students with high BSPS, highlighting that instructional effectiveness depends on students’ initial skill levels and support the development of adaptive learning strategies in science education.
Reach audiences
Advertise in front of researchers, engineers, and readers.
Large language models produce prompt-dependent probabilities over words, whereas scientific systems require uncertainty over meaningful states that can be updated as evidence arrives. We develop an observable framework for determining when language-derived probabilities support such a sequential state representation. T...
There are distributions that can be efficiently generated by a quantum learner with access to quantum samples, but not by a quantum learner with access to only classical samples, making progress to answering this question in the affirmative.
We propose a novel Mixture-of-Experts framework, referred to as Expert Loss Integration MoE (EliMoE), for time series forecasting. EliMoE addresses the optimization problem arising from small gating weights by incorporating expert-specific losses, which provide each expert with a direct learning signal independent of t...
Score-based diffusion models are a recently developed framework for posterior sampling in Bayesian inverse problems, enabling high-quality reconstructions in inverse problems by leveraging expressive prior distributions learned from empirical data. Despite their strong empirical performance and growing interest within...
Privacy preservation is critical in many high-stakes domains such as medicine and finance, where sensitive data must be analyzed without compromising individual confidentiality. At the same time, these applications often involve datasets with inherent missing values due to non-response or data corruption for example. M...
The various kernel methods that are encountered are surveyed and it is shown that each can be derived from one or the other of two competing strategies: *projection* or *restricted reconstruction*.
We endeavour to estimate numerous multi-dimensional means of various probability distributions on a common space based on independent samples. Our approach involves forming estimators through convex combinations of empirical means derived from these samples. We introduce two strategies to find appropriate data-dependen...
A utility-based framework that incorporates the consequences of decisions for the affected individuals and groups into the assessment of fairness and shows that a decision-making process can satisfy $\varepsilon$-fairness while nevertheless being maximally unfair once the utilities associated with its outcomes are take...
MIT Statistics and Data Science Center Director Alexander (Sasha) Rakhlin shares important considerations for departments and institutions.
MIT Statistics and Data Science Center Director Alexander (Sasha) Rakhlin shares important considerations for departments and institutions.
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.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
