arXiv:2602. 10751v3 Announce Type: replace Abstract: We study the problem of predicting numeric labels that are constrained to the integers or to a subrange of the integers.
arXiv:2207. 12877v3 Announce Type: replace Abstract: Motivated by the successes of deep learning, we propose a class of neural network-based discrete choice models, called RUMnets, inspired by the random utility maximization (RUM) framework.
arXiv:2607. 05908v1 Announce Type: new Abstract: Real-world data distributions evolve over time, inducing temporal distribution shift that can substantially degrade the reliability of deployed machine learning systems.
CG4AI is a column generation framework that trains AI models while enforcing linear constraints on their outputs. It constructs a convex combination of models, using a master linear program to set mixture weights and a pricing subproblem to generate new models guided by dual variables, focusing on the most violated constraints. The method is applied to MNIST digit classification—demonstrating constraint learning, adversarial robustness, error correction, and output relabeling—and to multi‑commodity flow routing, achieving feasible predictors with higher accuracy than single‑model baselines.
Over the past decade, deep neural networks (DNNs) have achieved remarkable success on complex machine-learning tasks, yet the theoretical foundations of their performance remain incomplete. From a statistical viewpoint, a natural question is: can DNNs attain feature-learning and prediction consistency comparable to that of classical models?
arXiv:2507. 05164v2 Announce Type: replace-cross Abstract: In this chapter, we utilize dynamical systems to analyze several aspects of machine learning algorithms.
arXiv:2206. 04359v3 Announce Type: replace Abstract: One of the fundamental challenges in the deep learning community is to theoretically understand how well a deep neural network generalizes to unseen data.
arXiv:2609.25728v1 Announce Type: new Abstract: Self-supervised learning for combinatorial optimization has emerged as a promising paradigm for solving discrete optimization problems with neural netw...
arXiv:2509. 23052v2 Announce Type: replace Abstract: We present a new meta-learning method to determine the optimal learning rate schedule for gradient descent.
arXiv:2509. 11285v2 Announce Type: replace-cross Abstract: Class-Incremental Learning (CIL) in deep neural networks is conventionally framed as an iterative gradient-based optimization problem, incurring high computational cost, hyperparameter sensitivity, and risk of catastrophic forgetting.
arXiv:2510.17072v2 Announce Type: replace Abstract: Regression with non-Euclidean responses---e.g., probability distributions, networks, symmetric positive-definite matrices, and compositions---has b...
arXiv:2608. 05454v1 Announce Type: new Abstract: Probabilistic prediction heads in neural networks typically output either a Gaussian mixture or a single conformal region.
The paper introduces asymptotically-informed neural‑network architectures for computing Black‑Scholes implied volatility. By learning a trainable partition of the price‑log‑moneyness domain and combining specialised local approximations, the models outperform standard feed‑forward networks across a wide range of parameters. The neural‑network outputs also serve as highly accurate initial guesses for a third‑order Householder scheme, enabling near machine‑precision results after only two refinement iterations.