Many of the most important datasets in the physical sciences live natively on the sphere, and these data often carry no preferred position or orientation. Using methods that do not reflect this symmetry leads to far higher simulation requirements, which can be catastrophic for scientific analyses (forcing reliance on c...
Joshua Williamson, N. Jeffrey, L. Whiteway· 0 citations
R\`enyi differential privacy, based on R\`enyi divergence, has become a notion of choice for privacy guarantees. However, outside the Gaussian setting, R\`enyi divergence can be difficult to compute. In particular, R\`enyi differential privacy guarantees that exploit task-specific information, as in R\`enyi Pufferfish...
Primal-dual methods for constrained Markov decision processes are analyzed under a two-timescale assumption, with non-stationarity entering through two channels, with non-stationarity entering through two channels under a common modulation and an isotropy condition.
Understanding how stochastic gradient descent learns internal representations in wide neural networks trained on rich target functions is a central problem in machine learning. We study this question in two-layer neural networks learning target functions represented by networks of the same architecture, with arbitrary...
Shu Zhou, Jean Barbier, Sebastian Goldt· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
It is shown how these boundaries can be directly coupled with a separate algorithmic analysis that derives the one-step recursion to provide a class of readymade anytime-valid envelopes across diverse settings including stochastic gradient descent (SGD), temporal difference learning, and Bures-Wasserstein SGD.
Learning causal structure from data requires assumptions about mechanisms, noises, observation schemes, and interventions. Historically, causal discovery has relied primarily on conditional independence. This review focuses on modern causal discovery methods that exploit properties of distributions beyond conditional i...
We introduce a conformal prediction framework for regression with Grassmann-valued responses. The proposed method constructs prediction regions in the form of metric balls directly on the Grassmann manifold, using basis-invariant geometric distances as non-conformity measures and scaling the corresponding non-conformit...
Dimitrios Loukrezis, Zachary J. Grey, Dimitris G. Giovanis· 0 citations
We consider the problem of online linear classification, where a stream of unlabeled samples is available, and annotation is costly. We investigate the optimal query policy, that prescribes whether and when a sample should be labeled and used for a training step, or instead discarded, so as to minimize a given objectiv...
Hugo Cui, Francesca Mignacco, Francesco Mori· 0 citations
Often, \emph{eg} in healthcare and predictive maintenance, what matters is which of several competing causes will strike first, and with what probability: survival analysis with competing risks. Corresponding deep learning methods are developed as bundles: a new architecture together with a new training loss, tested on...
Conformal test martingales (CTMs) are e-processes for sequentially testing exchangeability via p-values produced by a conformity function $A$. However, any distribution shift that preserves the push-forward $P\circ A^{-1}$ leaves the p-value distribution invariant, rendering it invisible to every CTM based on $A$. We f...
We study distinguishability and recovery of a sparse rank-one signal in a spiked Wigner model with independently sparse noise through a variety of algorithms and parameter regimes. The signal and noise have separate sparsity parameters, while the signal-to-noise ratio (SNR) remains of constant order as the matrix size...
Conformal Policy Selection combines weighted conformal $p$-values that account for the distributional shift from behavior to target policy with a two-step selection-and-pruning procedure, and establishes a doubly robust asymptotic guarantee.
Jun-Yu Cao, Rui-Jiang Gao, M. Saar-Tsechansky et al.· 0 citations
Is your company’s AI sovereign? A practical guide for CIOs on AI vendor lock-in, EU Data Act switching, cloud sovereignty, and testing your exit plan before you need it. The post Sovereignty Is the Option to Leave appeared first on GPT-Lab.
