Category
2,788 papers
This work establishes the first curvature-independent regret guarantees for decentralized online optimization on Hadamard manifolds, and studies Distributed Riemannian Online Gradient Descent, which combines local Riemannian h-subgradient updates with an implicit Fr\'echet-mean consensus.
This paper shows that a single algorithm achieves $\widetilde{\mathcal{O}}(\sqrt{(S+1)KT})$ expected regret for every $S$ against an oblivious adversary, resolving an open problem of Auer et al.
SAILS fills a notable gap in the eXplainable AI (XAI) toolbox, going beyond detecting interactions alone to characterizing their functional form, with limitations under strong feature correlations and higher-order interactions.
By reformulating MI estimation as an inference task, InfoAtlas establishes a foundation for real-time dependency analysis and generalizes effectively to complex, real-world scenarios.
Reach audiences
Advertise in front of researchers, engineers, and readers.
Large language models are increasingly used for clinical text classification, where overconfident misclassifications can directly affect patient care. Existing black-box uncertainty methods attach a confidence score to a fixed LLM prediction using softmax probabilities, verbalised confidence, prompt agreement, or gener...
Predictive likelihood ratios that average over uncertain probability deficits and residual-tail distributions are constructed, showing robustness across the evaluated alternatives, not uniform power guarantees or resistance to arbitrary text edits.
This study addresses the PU classification problem under violations of the SCAR assumption. We investigate logistic regression-based approaches, namely the cluster method and its extensions with strict and non-strict Lasso regularization. The primary contribution of this work is the integration of the SMOTE technique t...
We establish the equivalence between the stochastic optimal control and path space formulations of the Schr\"odinger bridge problem (SBP) for the kinematic equation on a compact connected Lie group. Using the geometric concepts of horizontal lift and stochastic anti-development, we derive a Girsanov-type change-of-meas...
As compute scales, models evolve, and training algorithms advance, our ability to explain the increasingly powerful AI systems they enable is eroding. To help safeguard interpretability, we introduce a specialized training algorithm (MACCHIATO) that jointly constructs (i) an explicitly structured $\operatorname{ReLU}$-...
Medical image classification is frequently complicated by transitional categories whose feature distributions overlap those of adjacent classes, producing ambiguous decision boundaries. Conformal prediction returns uncertainty-aware prediction sets, but these are not directly actionable in clinical screening, where a s...
ReGeoDTA is developed, a representation-preserving framework that maintains affinity-relevant chemical heterogeneity in molecular representations and continuous geometric relationships in protein structures that identifies representation fidelity as an upstream design principle for accurate and generalizable drug--targ...
A CTD approach that decouples convergence and diversity into two stages, aiming to quickly drive the search toward a single point on the Pareto front and focuses on diversity, aiming to spread solutions across the front.
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 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.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
