Category
3,048 papers
A perturbative regime in which the central flow is the limit of gradient descent, and the central flow emerges as the leading-order term in the expansion, while the self-stabilization mechanism appears in the next-order term.
This work introduces Pref-MH, a general exact MH sampler for judge-induced conditional distributions using only stochastic binary pairwise comparisons, and develops a valid accept/reject rule whose resulting Markov chain provably converges to the target distribution.
A rule is given that predicts that abstention driven by a wrong-signed score turns out worse than abstention at random on every dataset the authors test, and abstention driven by a wrong-signed score turns out worse than abstention at random on every dataset they test.
Supporting results include a second-moment identity that predicts stacking outcomes from measured correlations, an optimal-recovery certificate, and a distribution-free coverage band, the only uncertainty signal that survives the authors' tests.
Reach audiences
Advertise in front of researchers, engineers, and readers.
This paper shows that the problem of computing the stochastic probability (shortest code length) of the encoded vectors containing cluster structure using Normalized Maximum Likelihood (NML) model is a tractable problem by introducing a recursion formula for the efficient computation of normalizing constant from the NM...
Persistent entropy is a scalar summary of persistence barcodes widely used to detect regime changes, yet there is no account of when a structural change in a barcode must produce a detectable change in entropy. We establish a model-agnostic theorem supplying such conditions. Treating persistence diagrams as random obje...
This paper proposes algorithms that model online fair division as a contextual bandit problem and achieve provable sublinear regret and proposes algorithms that model utility is an unknown function of item-agent features.
This work studies multiplicity from the perspective of auditing incorrect ensemble predictions, where the decision to divert an instance for human review is based on a consistency criterion that combines the ensemble margin with a measure of local prediction variability for each constituent model.
Uniform-state discrete diffusion models update all tokens in parallel while keeping every position revisable. Even when the commonly used top-$p$ rule leaves only one candidate at a position, that choice affects only the current reverse step and can be revised at the next sampling step. We ask what changes when selecte...
Embedded CITs (eCITs), which embed X and Z and apply an existing CIT to the resulting representations and to the resulting representations, are proposed and it is shown that sufficiency weakens to mean sufficiency when the embedded test targets conditional mean independence.
Fed-LSVI is proposed, the first provably efficient federated algorithm for online reinforcement learning with linear function approximation in episodic Markov decision processes and achieves a regret bound of $\widetilde{\mathcal O}(\sqrt{Md^3H^4T})$, matching the best-known regret for multi-agent online reinforcement...
This systematic literature review synthesizes interdisciplinary evidence on how AI transforms leadership and management functions, drives business model innovation, and alters workplace dynamics, with particular attention to Southeast Asian and Philippine contexts.
General Science
Accelerating the search for novel antimicrobial peptides using Google Antigravity for Science.
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar appeared first on Microsoft Research.
General Science
General Science
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
