This work proposes a stratified greedy algorithm that maximizes a heteroscedastic information-gain objective and proves that the objective is monotone and submodular under query-dependent noise, so stratified greedy selection carries a 1/2-approximation guarantee under the partition constraint.
DOMD-GLB is proposed, a new algorithm for nonstationary GLBs that utilizes discounted online mirror descent (DOMD) for parameter estimation, thereby incurring only $O(1)$ computation and memory costs per round, the first algorithm for nonstationary GLBs with per-round computation and memory costs independent of time.
The functional ANOVA provides a fundamental representation of square-integrable multivariate functions into main effects and higher-order interactions. For independent inputs, the components belong to mutually orthogonal Hilbert subspaces and admit an explicit representation. For dependent inputs, however, the componen...
Baptiste Ferrere, Nicolas Bousquet, Fabrice Gamboa et al.· 0 citations
BroxGD is proposed, a projection-free sister method to projected gradient descent for constrained optimization for constrained optimization that expects to find many applications and inspire numerous extensions, much like projected gradient descent.
Peter Richtárik, Kaja Gruntkowska, Han-Min Li· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work introduces Multiscale Euclidean Network Trajectories (MENT), whose central estimands are pairwise second-moment operators of the dynamic latent positions of the dynamic latent positions, whose central estimands are pairwise second-moment operators of the dynamic latent positions.
This work provides a formal definition of SROT, derives its dual formulation, and provides a post-Bayesian interpretation of SROT, and develops a Sinkhorn-style algorithm for efficient computation, retaining the same scalability advantages as EOT.
We introduce a robust conformal prediction method based on the half-mass radius $\dP(x):=\inf\{r>0:P(B(x,r))>1/2\}$. Its empirical version is exactly the distance from a point to its $\mathbf{k}$-th nearest neighbour, with $\mathbf{k}=\lfloor n/2\rfloor+1$. The resulting conformal sets retain finite-sample marginal val...
A. Cholaquidis, Émilien Joly, L. Moreno· arXiv.org· 0 citations
We introduce the exponentially weighted signature (EWS), a continuous-time model that computes iterated integrals of a path, where each increment is weighted by the matrix exponential of a learnable generator over elapsed clock time. We prove that it solves a linear controlled differential equation, keeps the group-lik...
Alexandre Bloch, Benjamin Walker, Joel Mouterde et al.· 1 citation
AI systems increasingly assist decision making by producing cheap factor-level assessments of complex inputs, but these assessments can be biased or incomplete. We study selective human evaluation: given AI signals, which factors should be dispatched to human experts? We formulate this human--AI collaboration problem a...
Lezhi Tan, Naomi Sagan, Lihua Lei et al.· 0 citations
It is proved that $\Gamma-convergence of regularized empirical risk minimization functionals and corresponding convergence of their global minimizers, in the sense of weak convergence of the parameter measures and uniform convergence of the functions over compact sets, provides a formalization of mesh and sample indepe...
Johanna Tengler, Christoph Brune, J. A. Iglesias· arXiv.org· 1 citation
This paper shows that minimizing the Kullback-Leibler divergence between a policy-driven true distribution and a reward-driven model distribution for a suitably defined action-driven process is equivalent to maximum entropy reinforcement learning.
A stochastic approximation framework for learning nonlinear operators between infinite-dimensional spaces utilizing general Mercer operator-valued kernels and vector-valued interpolation spaces is developed, thereby enabling rich structural modeling with rigorous theoretical guarantees.
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.
