Category
2,654 papers
These are the first non-asymptotic R\'enyi-divergence tracking bounds for Langevin dynamics with discrete target updates for Langevin diffusion and Langevin Monte Carlo.
Antibody lead optimization calls for a small, bounded set of edits to an existing candidate: substitutions, but also insertions and deletions. Edit-based generative models are the only ones that allocate such an edit budget without fixing the edit positions, the edit count, or the output length in advance. However, the...
This paper solves the problem of sign-based variance reduction methods' failure to obtain optimal convergence rates for both nonconvex stochastic and finite-sum optimization, and proposes tracking the global gradient at the server through unbiased compression of recursive gradient increments.
Classifiers can make identical predictions yet require labels to compare their selective performance: confidence ranks weight the same errors differently. We quantify this requirement for the area under the generalized risk-coverage curve (AUGRC). A prelabel lower bound rules out insufficient budgets. With all labels k...
Reach audiences
Advertise in front of researchers, engineers, and readers.
An algorithm is proposed that iteratively identifies terminal (observed) nodes and reconstructs the directed acyclic graph of the observed variables as a sparse plus low-rank matrix that correctly identifies the directed causal relationship among observed variables.
Experimental results and decoupling ablations demonstrate that SANI consistently improves Fr\'echet Inception Distance (FID) over the vanilla DDPM and DDIM endpoint samplers across diverse sampling timesteps, while remaining competitive with variance-learning baselines, highlighting the importance of spatial adaptivity...
This work connects Adam loss spikes to both the mismatch between momentum timescales and finite-scale superquadratic loss geometry beyond the Hessian, and shows that confident cross-entropy losses develop a core--wall landscape comprising a narrow quadratic core followed by a steep wall, which produces effective superq...
The problem of identifiability in linear parametric models (LPMs) whose nodes follow either an ordered logit model or a regular one-parameter exponential family is evaluated. The results go beyond classical structural equation models as well as results for nodes with observations from a homogeneous family of distributi...
The standard geometric derivation of neural scaling exponents takes the intrinsic dimension of a data manifold as its input. On modular addition in $\mathbb{Z}_p$ that derivation has no input. The exact algebraic solution is an orbit of $\mathbb{Z}_p$ acting by isometries. Transitivity alone makes the ratio statistic u...
We introduce TabPFN-3.5, our new flagship Tabular Foundation Model. It significantly outperforms its predecessor, TabPFN-3, and all existing baselines across a broad range of tabular problems. TabPFN-3.5 sets a new state of the art on standard tabular prediction in TabArena, and extends it to the data practitioners enc...
Artificial intelligence (AI) is moving increasingly beyond prediction to support decisions in complex, uncertain, and dynamic environments. This shift creates a natural intersection with operations research and management science (OR/MS), which has long provided methodological foundations for sequential decision making...
Several novel results related to transfer learning are proved, showing the need to carefully select which sets of information to transfer and the need for dependence between transferred information and target problems and how the degree of probabilistic change in an algorithm using transfer places an upper bound on the...
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.
