Category
2,618 papers
iKFAD is a recently proposed optimiser that replaces adaptive learning rates with adaptive friction in the momentum dynamics, yet performs as well as Adam. Its limitation is that the full friction tensor $\xi\in\mathbb{R}^{m\times n}$ carries the same $\mathcal{O}(mn)$ memory overhead per layer as Adam's second-moment...
Adaptive arm selection changes the distribution of the observations collected by a bandit algorithm, but it need not change their limiting empirical spectrum. We study Gaussian bandit designs in which the dimension and the number of observations grow proportionally. A quantitative coupling theorem compares the design g...
Machine Learning and more specifically Deep Learning involves solving large scale nonconvex optimization problems. Several algorithms have been proposed in the literature, that seem to achieve satisfactory practical efficiency for difficult instances, the Stochastic Gradient Method being the most rudimentary, while sti...
A unified pipeline for univariate time series classification via complex networks and persistent homology is presented, showing that no single construction dominates and persistence-based features degrade gracefully under noise, consistent with the classical stability theorem of persistent homology.
Reach audiences
Advertise in front of researchers, engineers, and readers.
In this article, we define a new non-archimedean metric structure, called cophenetic metric, on persistent homology classes of all degrees. We then show that zeroth persistent homology together with the cophenetic metric and hierarchical clustering algorithms with a number of different metrics do deliver statistically...
A penalized DRO formulation in which the adversary may choose any distribution but incurs a Wasserstein penalty for deviating from the empirical distribution is studied, showing that the adversary's problem can be reformulated as an optimization problem over transport maps that push empirical samples to adversarial one...
A regime-adaptive deconfounding layer that first estimates the confounding regime from data using a Mar\v{c}enko--Pastur spectral router, then applies a deconfounding strategy matched to that regime, which attenuates factor-dominated variation and recovers contemporaneous structure from the resulting innovations.
A Sampling-Aware Global Evaluation (SAGE) benchmark is introduced, combining GBIF records for training with sPlotOpen vegetation plots for presence-absence evaluation across 5771 plant species, and an evaluation framework that groups species based on two properties, sampling effort and relative prevalence is proposed.
It is shown that minimizing cross-entropy can be misaligned with minimizing verifier risk; two policies can assign identical likelihood to the observed demonstrations while placing different probability mass on incorrect outputs, and entropy-regularized training consistently improves verifier accuracy over standard cro...
Sequential inference estimates latent states from noisy and incomplete observations. Particle Filters (PFs), a class of Monte Carlo methods based on importance sampling, provide a flexible framework for this task, but often suffer from poor sample efficiency and unfavorable scaling with dimension, partly due to subopti...
A functional neural network for learning trajectories on the Riemannian manifold of symmetric positive definite (SPD) matrices, termed MatFAE, which features intrinsic layers that map manifold-valued functions to Euclidean vector-valued functions, followed by a functional layer that projects them into a finite-dimensio...
Modern recommendation systems increasingly rely on dynamically routing diverse queries to multiple embedding models. Despite its practical significance, this problem remains poorly understood under realistic conditions like adversarial queries, bandit feedback, and limited observability of models. We formalize embeddin...
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.
Mobile Systems
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
