Statistical Learning
A Batch-to-Online Transformation under Random-Order Model
In online learning literature, stochastic and adversarial settings are two of the most well-studied cases.
Unified Embedding: Battle-Tested Feature Representations for Web-Scale ML Systems Benjamin Coleman
Learning high-quality feature embeddings efficiently and effectively is critical for the performance of web-scale machine learning systems.
Individualized Dosing Dynamics via Neural Eigen Decomposition
Dosing models often use differential equations to model biological dynamics.
Coordinating Distributed Example Orders for Provably Accelerated Training
Whereas RR arbitrarily permutes training examples, GraB leverages stale gradients from prior epochs to order examples -- achieving a provably faster convergence rate than RR.
CD_GraB_camera_ready
Whereas RR arbitrarily permutes training examples, GraB leverages stale gradients from prior epochs to order examples -- achieving a provably faster convergence rate than RR.
We present conditional monotonicity results using alternative estimators of performance quality
The Appendix is structured as follows: We provide a proof of conditional guarantees in EENNs for (hard) PoE in Appendix A . We conduct an ablation study for our P A model in Appendix B.2 . We report results of NLP experiments in Appendix B.4 . We discuss anytime regression and deep ensembles in Appendix B.6 . We propose a technique for controlling the violations of conditional monotonicity in P A in Appendix B.8 .
Learning via Wasserstein-Based High Probability Generalisation Bounds
The authors contributed equally to this work 37th Conference on Neural Information Processing Systems (NeurIPS 2023). Developing upper bounds on the generalisation gap, i.e., generalisation bounds has been a longstanding topic in statistical learning.