We study the generalization of spectral gradient descent (SpecGD) in overparameterized matrix classification with corrupted labels. Each input combines a shared low-rank signal with a rank-one sample-specific perturbation, referred to as a shortcut, that enables memorization but does not generalize. We contrast collaps...
This work model SGD gradient noise by adopting a Young function that preserves the finiteness of all polynomial moments while allowing tails heavier than sub-Weibull, including lognormal distributions, and establishes concentration inequalities for $\beta$-heavy-tailed noise.
Nonlinear dynamical systems with memory arise across science and engineering, yet uncertainty quantification for efficient forecasting methods such as Next Generation Reservoir Computing (NGRC) remains underdeveloped. We study Bayesian ridge and conformal prediction intervals for NGRC and characterize when their uncert...
L. Popa, Sumanta Basu, Martin T. Wells· 0 citations
It is proved that \textsc{FOCUS} is $(\epsilon,\delta)$-correct and that its expected stopping time matches the lower bound in its $\Theta(\log(1/\delta)$ dependence up to an instance-dependent constant.
Hai-Jie Xu, Chen Zhang· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Linear bandits model sequential decision-making problems with noisy rewards that are linear in the decision variable, where an agent must simultaneously learn about an unknown parameter that governs the mean rewards, while maximizing (expected) rewards over time. Two prominent algorithmic families--upper confidence bou...
Arda Güçlü, Subhonmesh Bose, J. Birge· 0 citations
Physical systems evolve continuously in time, yet their states are typically observed only at discrete times. Generating trajectories consistent with their probability densities from such observations therefore requires capturing the continuous-time evolution rather than only learning transition mappings between consec...
Generating independent, equilibrium samples of molecular systems at scale remains a central obstacle in computational statistical mechanics. Boltzmann Generators address this by pairing a generative model with importance sampling to obtain consistent samples from the target distribution. We introduce Normalizing Flow F...
Louis Grenioux, Rui-Kang Ouyang, Lu-Huan Wu· 0 citations
Multiple instance learning (MIL) is widely used in computational pathology because it enables weakly supervised analysis of whole-slide images (WSIs) without requiring patch-level annotations. In attention-based MIL, instances with high attention scores are often interpreted as diagnostically important regions and used...
Noriaki Hashimoto, Shuichi Nishino, Teruyuki Katsuoka et al.· 0 citations
We study the minimum number of hidden neurons required for arbitrary-accuracy approximation of multivariate H\"older-continuous functions on $[0,1]^d$ and the associated encoding complexity. For $d\geq 2$, we construct a fixed, explicitly defined activation function for which a closed-form network with two hidden layer...
Joint-embedding predictive architectures enable planning with latent world models, but accurate transition prediction alone does not ensure that the planning objective is easy to optimize. We introduce Control-Geometry Straightening (CGS), a single auxiliary loss that learns planner-friendly representations by directly...
Simplex Diffusion Models (SDMs) are proposed, a framework that lifts the diffusion process to the probability simplex to represent beliefs over categories and can carry uncertainty across denoising steps, which mitigates information collapse.
Justin Deschenaux, Alexandre Galashov, Andrew Campbell et al.· 1 citation
Many learning tasks map an input distribution to an output distribution. A natural way to model such an operator is to transform each input sample using a continuous function that may depend on the entire input distribution, and then take the distribution of the transformed samples. This defines a measure-dependent pus...
Takashi Furuya, Nicholas H. Nelsen, Frank Cole· 0 citations
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.
