Sparsity is a powerful structural resource in optimization and statistics. We develop frameworks for leveraging sparsity in sampling problems over the Hamming slice $\mathcal{X}_k^d:=\{\mathbf{x}\in\{\pm 1\}^d:|\{i:\mathbf{x}_i=1\}|=k\}$, in high-dimensional regimes where $k\ll d$ (i.e., where $\mathcal{X}_k^d$ is \emp...
Syamantak Kumar, Purnamrita Sarkar, Kevin Tian et al.· 0 citations
In this paper, we consider the scalar-on-function linear regression model under a realistic sampling scheme in which the functional covariates are observed on a regular grid and contaminated by additive noise. We propose a two-step estimation procedure: first, the underlying curves are reconstructed from the discrete n...
This work identifies the minimum interval budget needed to retain the unrestricted 1-bit minimax sample rate and determines the minimax sample complexity among non-adaptive 1-bit estimators when every one-set $Q^{-1}(1)$ is restricted to a union of at most $s$ intervals.
We study the time-uniform convergence of the raw iterate of standard stochastic gradient descent (SGD) for unconstrained smooth convex objectives. We prove that, under standard noise assumptions, the time-uniform convergence rate gets arbitrarily close to $\sqrt{\log n / n}$ but never reaches it. More specifically, we...
Rui-Jie Li, Kang Chen, Tian-Yu Wang· 1 citation
Reach audiences
Advertise in front of researchers, engineers, and readers.
The Conformal LOwer bound on Changepoint Count (CLOCC) is shown to be the only feasible way to provide a lower bound on K under the stated assumptions, a property it is referred to as its universality.
A Fisher-information flow speed limit is derived that bounds the rate at which trainable parameters can acquire information about latent variables in the data-generating process and establishes Fisher-information speed limits as a quantitative framework for diagnosing when and how different aspects of the data-generati...
Simulations demonstrate that the tuning schemes reliably yield near-optimal slice-adaptive tuning with essentially no dependence on the initial setting of $w$, and develop automated, slice-adaptive tuning schemes along with suboptimality bounds and asymptotic convergence guarantees.
This paper moves beyond point estimation and discusses frequentist and Bayesian approaches to uncertainty quantification for fair machine learning, with practical examples and implications for simulated and real data.
Francesca Panero, Ernst C. Wit, Marco Scutari· 0 citations
Theoretical scaling laws from linear regression to multiclass classification to multiclass classification are extended, while connecting to empirical scaling laws observed in large-scale neural networks.
Konstantinos Christopher Tsiolis, Denny Wu, Christos Thrampoulidis et al.· 0 citations
The Proximal Bouncy Particle Sampler is a new sampler that combines ideas from the proximal sampler and the bouncy particle sampler that returns a sample whose law is $\varepsilon$-close to $\mu$ in total variation distance using gradient queries in expectation.
Fan Chen, Sinho Chewi, Jian-Feng Lu et al.· 0 citations
The adaptive classification-risk design attains lower mean error than this Fisher comparator across the labeling budgets considered, although it does not uniformly outperform entropy or margin sampling and differences among the targeted strategies become small as the labeling budget increases.
F. Setoudehtanzangi, Geoffrey J. McLachlan· 0 citations
A tokenwise formula for the error of reusing one query's matrix is derived and it is proved that a nonconstant finite-cache head cannot admit a globally exact affine query readout.
Julie Huang, Maggie Chlon, Leon Chlon· 0 citations
A machine-learning approach called CheMeleon provides a practical way to develop new drugs or other molecules with much less detailed, expensive experimentation.
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.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
