arXiv:2506.08921v2 Announce Type: replace-cross Abstract: We consider the problem of propagating the uncertainty from a possibly large number of random inputs through a computationally expensive model. Stratified sampling is a well-known variance reduction strategy, but its application, thus far, has focused on models with a limited number of inputs due to the challenges of creating uniform partitions in high dimensions. To overcome these challenges, we propose a simple methodology for constructing an effective stratification of the input domain […]

Ver mais

arXiv:2502.01861v3 Announce Type: replace-cross Abstract: When training large models on limited data, avoiding overfitting is paramount. Common grid search or smarter search methods rely on expensive separate runs for each candidate hyperparameter, while carving out a validation set that reduces available training data. In this paper, we study gradient-based learning of hyperparameters via the evidence lower bound (ELBO) objective from Bayesian variational methods. This avoids the need for any validation set. We focus on scenarios where the model […]

Ver mais

Reinforcement learning (RL) in mobile edge computing (MEC) faces critical challenges of data heterogeneity, communication overhead, and limited generalization across diverse preferences and system configurations. We propose Adaptive Reinforcement Learning Offloading (ARLO), a unified framework integrating adaptive dissimilarity measures for federated learning with generalizable multi-objective optimization for computation offloading. The Adaptive Dissimilarity Measure module leverages parameter dissimilarity with Lagrangian multipliers to mitigate model drift under Non-IID data and loss dissimilarity to reduce communication overhead via adaptive aggregation. The […]

Ver mais

arXiv:2601.16070v1 Announce Type: new Abstract: Deep neural networks (DNNs) typically involve a large number of parameters and are trained to achieve zero or near-zero training error. Despite such interpolation, they often exhibit strong generalization performance on unseen data, a phenomenon that has motivated extensive theoretical investigations. Comforting results show that interpolation indeed may not affect the minimax rate of convergence under the squared error loss. In the mean time, DNNs are well known to be highly vulnerable to […]

Ver mais

arXiv:2604.01373v1 Announce Type: new Abstract: Estimating the dissipativity of nonlinear systems from empirical data is useful for the analysis and control of nonlinear systems, especially when an accurate model is unavailable. Based on a Koopman operator model of the nonlinear system on a reproducing kernel Hilbert space (RKHS), the storage function and supply rate functions are expressed as kernel quadratic forms, through which the dissipative inequality is expressed as a linear operator inequality. The RKHS is specified by […]

Ver mais

I’ve been working on an educational implementation repo for speculative decoding: https://github.com/shreyansh26/Speculative-Decoding The goal is not to wrap existing libraries, but to implement several speculative decoding methods from scratch behind a shared decoding/evaluation contract so that the differences between proposer designs are easier to study. Implemented methods so far: EAGLE-3 Medusa-1 standard draft model speculation PARD / parallel draft models n-gram prompt lookup suffix decoding The repo has both training and inference paths where applicable. For learned proposers, […]

Ver mais