Category
2,788 papers
HyCoSeq incorporates weighted Lorentzian residual aggregation into multi-curvature Lorentz encoding, allowing full Lorentz representations to participate directly in geometry-consistent local aggregation, thereby extending local hyperbolic convolutional encoding to sequence-level contextualized representations.
Variational modeling is highlighted as a complementary approach to robust long-horizon neural PDE dynamics by introducing latent Markov dynamics, which combines spatially resolved latent fields, structured Gaussian perturbations, and a neural-operator transition.
Bounded predictive influence and reliability-guided geometry as complementary mechanisms for imbalanced learning with uncertain labels are supported as complementary mechanisms for imbalanced learning with uncertain labels.
Prototype reduction replaces a training set with a smaller representation, and the established methods return a finite set of points. We propose Skeletal Prototypes on Iterative Nerve Expansions (SPINE). The model for each class is an embedded 1-complex rather than a point set. Its initial edge set is a class-condition...
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work extends operator-informed GP regression to complex-valued Helmholtz problems by realifying the complex operator into an equivalent coupled real block, which enables inference with standard real-valued GP conditioning and identifies a low-frequency accuracy ceiling set by model mismatch and a posterior uncerta...
This work derives Renyi-DP guarantees separating privacy leakage through the posterior mean from a distinct channel induced by the data-dependent posterior covariance, and identifies effective ridge regularisation and covariance scale as the principal privacy-controlling quantities.
The classic concept of"calibrated forecasts"and its more recent refinement,"calibeating,"are defined with respect to the standard quadratic scoring rule. We extend these notions to the class of proper scoring rules (for which the true distribution is an optimal forecast) and define \textit{proper calibration} and \text...
We study optimal learning rate (LR) schedules under the functional scaling law (FSL) framework (Li et al., 2025), which decomposes training dynamics into signal learning and noise forgetting. In power-law kernel regression, these two components are governed by a source exponent $s>0$ and a capacity exponent $q>1$, resp...
We study exact community recovery in sparse directed stochastic block models using neighborhood smoothing of connection-probability profiles. The proposed method clusters vertices according to their estimated outgoing connection-probability profiles. For each vertex, its complete outgoing profile is estimated by averag...
In this work, we introduce $\textit{basic inequalities}$ for first-order iterative optimization algorithms, forming a simple yet versatile framework which connects implicit and explicit regularization. Building on related comparison inequalities for optimization iterates that already exist in the literature, we extend...
This work introduces an adaptive conformal inference method capable of efficiently handling deviations from exchangeability caused by random label noise, leading to informative prediction sets with tight marginal coverage guarantees even in those challenging scenarios.
This paper introduces the notion of upper-linearizable/quadratizable functions, a class that extends concavity and DR-submodularity in various settings, including monotone and non-monotone cases. A general meta-algorithm is devised to convert algorithms for linear/quadratic maximization into ones that optimize upper-li...
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.
