Category
2,791 papers
This work introduces Multistage Defer Trees: a sequence of sparse decision trees that each make predictions for most samples, while deferring a small proportion to the next tree in the sequence or, ultimately, to a black box.
Discrete diffusion has become a leading framework for generative modeling in various applications including language, vision, and biology. Existing convergence theory, however, exhibits fundamental limitations. KL-based analyses diverge under singular priors such as the masked distribution, while bounds in total variat...
This work proposes a refined analysis of the non-consecutive gradient variation, a fundamental quantity in gradient variation with bandit feedback, and improves the dimension dependence for both convex and strongly convex functions compared with the best known results.
Learning systems often expand their ambient features or latent representations over time, embedding earlier representations into larger spaces with limited new latent structure. We study transfer learning for structured matrix estimation under simultaneous growth of the ambient dimension and the intrinsic representatio...
Reach audiences
Advertise in front of researchers, engineers, and readers.
A local-valley (LV)-centered approach to assessing the quality of sampling from Restricted Boltzmann Machines (RBMs) was applied to the latest generation of the D-Wave quantum annealer, revealing some potential for improvement, e.g., using a combined classical–quantum approach.
We study neural architectures in which each hidden layer is defined by the stationary state of a dissipative Schr\"odinger-type dynamics on a learned latent graph. On stable branches, the local stationary problem defines a differentiable implicit graph layer. To learn the graph itself, we optimize over the stratified m...
The long horizon forecasting (LHF) problem has come up in the time series literature for over the last 35 years or so. This review covers aspects of LHF in this period and how deep learning has incorporated variants of trend, seasonality, fourier and wavelet transforms, misspecification bias reduction and bandpass filt...
This work derives a differential equation that governs the evolution of the generalization gap when a model is trained by gradient descent-based methods and shows that the generalization gap is given by a quadratic form that consists of an ``effective Gram matrix'' that depends upon the training trajectory and a certai...
Neural differential equations offer a powerful approach for learning dynamical systems from data. However, they do not inherently respect known constraints, such as conservation laws, that should be obeyed by the learned dynamics. It is well known that enforcing constraints in data-driven models can enhance their gener...
An online variant of the hard thresholding algorithm that performs the sparse estimation in an online manner is developed and embedded in a primal-dual scheme: every knapsack constraint is paired with a dual variable, which is updated by an online learning rule to keep the cumulative resource consumption within budget.
Two new algorithms for estimating the parameters of a latent class model for ordered categorical data with polytomous responses are introduced based on a newly defined regularized Laplacian matrix derived from the response matrix.
The equivalent loss is introduced, whose gradient is the original loss gradient multiplied by the query probability, which derives a finite-sample excess-risk bound with a fixed learning rate and an explicit constant controlling the tradeoff between initial error and query-weighted gradient variance.
General Science
General Science
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.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
