arXiv Statistics @arxiv_stats@qoto.org

Achieving acceleration despite very noisy gradients. (arXiv:2302.05515v1 [stat.ML]) http://arxiv.org/abs/2302.05515

Cyclic and Randomized Stepsizes Invoke Heavier Tails in SGD. (arXiv:2302.05516v1 [stat.ML]) http://arxiv.org/abs/2302.05516

Robust Knowledge Transfer in Tiered Reinforcement Learning. (arXiv:2302.05534v1 [cs.LG]) http://arxiv.org/abs/2302.05534

Balancing Approach for Causal Inference at Scale. (arXiv:2302.05549v1 [stat.ME]) http://arxiv.org/abs/2302.05549

Algorithmically Effective Differentially Private Synthetic Data. (arXiv:2302.05552v1 [cs.DS]) http://arxiv.org/abs/2302.05552

Optimal Sampling Design Under Logistical Constraints with Mixed Integer Programming. (arXiv:2302.05553v1 [stat.ME]) http://arxiv.org/abs/2302.05553

Higher-Order Allan Variance for Atomic Clocks of Arbitrary Order. (arXiv:2302.05556v1 [math.PR]) http://arxiv.org/abs/2302.05556

Windowed Fourier Analysis for Signal Processing on Graph Bundles. (arXiv:2302.05592v1 [eess.SP]) http://arxiv.org/abs/2302.05592

Communication and Storage Efficient Federated Split Learning. (arXiv:2302.05599v1 [cs.IT]) http://arxiv.org/abs/2302.05599

Information Theoretic Lower Bounds for Information Theoretic Upper Bounds. (arXiv:2302.04925v1 [cs.LG]) http://arxiv.org/abs/2302.04925

Efficient Propagation of Uncertainty via Reordering Monte Carlo Samples. (arXiv:2302.04945v1 [cs.LG]) http://arxiv.org/abs/2302.04945

Gaussian Process-Gated Hierarchical Mixtures of Experts. (arXiv:2302.04947v1 [cs.LG]) http://arxiv.org/abs/2302.04947

The Monge Gap: A Regularizer to Learn All Transport Maps. (arXiv:2302.04953v1 [cs.LG]) http://arxiv.org/abs/2302.04953

Using Echo State Networks to Inform Physical Models for Fire Front Propagation. (arXiv:2302.04960v1 [stat.ME]) http://arxiv.org/abs/2302.04960

Quadratic Memory is Necessary for Optimal Query Complexity in Convex Optimization: Center-of-Mass is Pareto-Optimal. (arXiv:2302.04963v1 [cs.LG]) http://arxiv.org/abs/2302.04963

Communication-Efficient Federated Hypergradient Computation via Aggregated Iterative Differentiation. (arXiv:2302.04969v1 [cs.LG]) http://arxiv.org/abs/2302.04969

Surrogate-Assisted Federated Learning of high dimensional Electronic Health Record Data. (arXiv:2302.04970v1 [stat.ME]) http://arxiv.org/abs/2302.04970

Differentially Private Optimization for Smooth Nonconvex ERM. (arXiv:2302.04972v1 [cs.LG]) http://arxiv.org/abs/2302.04972

Piecewise Linear and Stochastic Models for the Analysis of Cyber Resilience. (arXiv:2302.04982v1 [cs.CR]) http://arxiv.org/abs/2302.04982

Sample Complexity Using Infinite Multiview Models. (arXiv:2302.04292v1 [math.ST]) http://arxiv.org/abs/2302.04292