We consider the problem of support recovery for sparse binary signals from noisy linear measurements. For sparse Gaussian measurement matrices we identify sufficient conditions on the minimal sample size for maximum-likelihood recovery in the high-SNR regime $ds/p \to \infty$, where $p$ denotes the signal dimension, $s...
We introduce a novel privatization framework for high-dimensional controlled variable selection. Our framework enables rigorous False Discovery Rate (FDR) control under differential privacy constraints. While the Model-X knockoff procedure provides FDR guarantees by constructing provably exchangeable ``negative control...
Numerical experiments are performed finding that full Bayesian inference provides superior predictive performance relative to Trans-Lasso on a genetics application, especially when the source data are limited.
Nathan Wycoff, A. Arab, Lisa O. Singh· arXiv.org· 1 citation
Machine learning (ML) techniques have recently enabled enormous gains in sensitivity to new phenomena across the sciences. In particle physics, much of this progress has relied on excellent simulations of a wide range of physical processes. However, due to the sophistication of modern machine learning algorithms and th...
Malte Algren, Tobias Golling, Francesco Armando Di Bello et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
COVariate-ovERlap regularized multi-task learning (COVER) is proposed to address covariate and posterior heterogeneity and achieves the lowest response-averaged prediction error among the compared methods and reveals tissue-pair integration patterns.
This work proposes pruning (removing unnecessary variables) and clustering (combining variables) as preprocessing operations for causal data fusion and gives sufficient conditions for inferring the identifiability or non-identifiability of a causal effect in a larger graph based on a smaller graph.
Otto Tabell, S. Tikka, Juha Karvanen· arXiv.org· 4 citations
Score estimation is the backbone of score-based generative models (SGMs), especially denoising diffusion probabilistic models (DDPMs). A key result in this area shows that with accurate score estimates, SGMs can efficiently generate samples from any realistic data distribution (Chen et al., ICLR'23; Lee et al., ALT'23)...
Sinho Chewi, Alkis Kalavasis, Anay Mehrotra et al.· 0 citations
This work proposes a novel formalization of label flipping attacks as a per-round constrained optimization problem, derives a greedy label-selection rule for logistic regression, and empirically evaluates it beyond its derivation setting, including on MLPs and robust aggregators.
This paper establishes a collection of covering number bounds for linear function classes under various norm constraints on the inputs and matrices and explicitly incorporates rank constraints on the underlying matrix classes, allowing us to characterize how low-rank structures affect the metric entropy.
It is shown that EM recovers the mixture atoms at the parametric rate, up to logarithmic factors, after $\mathcal{O}(\log N)$ iterations, provided atom separation is at least of order $\log K$.
Xin Bing, F. Bunea, Jonathan Niles-Weed et al.· 1 citation
Offline reinforcement learning enables evaluation and optimization of sequential decisions from historical data, when it is not possible to deploy new policies online due to safety, cost, and other concerns. Big data advances enable rich state information, but may naively include reward- and action- irrelevant dynamics...
Mixed membership modeling for undirected networks has been extensively explored in network science over the past few years. Despite the substantial progress made for undirected cases, handling mixed membership structures in directed networks continues to pose substantial difficulties. To address this gap, we introduce...
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar appeared first on Microsoft Research.
Learn how Google DeepMind and GovTech Singapore uses lightweight on-device Gemma models to intercept conversational scams in private chats with zero cloud data egress.
MIT News · Artificial Intelligence· news.mit.eduOct 8, 2026
