Related papers: Autodeleveraging as Online Learning
Training Large Language Models (LLMs) is highly memory-intensive due to optimizer state overhead. The FRUGAL framework mitigates this with gradient splitting, but its static hyperparameters -- the subspace ratio ($\rho$) and update…
Privacy-preserving distributed machine learning (ML) and aerial connected vehicle (ACV)-assisted edge computing have drawn significant attention lately. Since the onboard sensors of ACVs can capture new data as they move along their…
The trade-off between regret and computational cost is a fundamental problem for online kernel regression, and previous algorithms worked on the trade-off can not keep optimal regret bounds at a sublinear computational complexity. In this…
Logistic Regression and Support Vector Machine algorithms, together with Linear and Non-Linear Deep Neural Networks, are applied to lending data in order to replicate lender acceptance of loans and predict the likelihood of default of…
This paper studies how to train machine-learning models that directly approximate the optimal solutions of constrained optimization problems. This is an empirical risk minimization under constraints, which is challenging as training must…
Online strategic classification studies settings in which agents strategically modify their features to obtain favorable predictions. For example, given a classifier that determines loan approval based on credit scores, applicants may open…
Model-based deep learning (MBDL) is a powerful methodology for designing deep models to solve imaging inverse problems. MBDL networks can be seen as iterative algorithms that estimate the desired image using a physical measurement model and…
Decentralized exchanges (DEXs) are crucial to decentralized finance (DeFi) as they enable trading without intermediaries. However, they face challenges like impermanent loss (IL), where liquidity providers (LPs) see their assets' value…
To alleviate the shortage of computing power faced by clients in training deep neural networks (DNNs) using federated learning (FL), we leverage the edge computing and split learning to propose a model-splitting allowed FL (SFL) framework,…
Deep Q-Learning (DQL), a family of temporal difference algorithms for control, employs three techniques collectively known as the `deadly triad' in reinforcement learning: bootstrapping, off-policy learning, and function approximation.…
Given any increasing sequence of norms $\|\cdot\|_0,\dots,\|\cdot\|_{T-1}$, we provide an online convex optimization algorithm that outputs points $w_t$ in some domain $W$ in response to convex losses $\ell_t:W\to \mathbb{R}$ that…
The theory of deep learning focuses almost exclusively on supervised learning, non-convex optimization using stochastic gradient descent, and overparametrized neural networks. It is common belief that the optimizer dynamics, network…
Online learning is a powerful tool for analyzing iterative algorithms. However, the classic adversarial setup sometimes fails to capture certain regularity in online problems in practice. Motivated by this, we establish a new setup, called…
In autonomous driving, even a meticulously trained model can encounter failures when facing unfamiliar scenarios. One of these scenarios can be formulated as an online continual learning (OCL) problem. That is, data come in an online…
How to quickly and automatically mine effective information and serve investment decisions has attracted more and more attention from academia and industry. And new challenges have arisen with the global pandemic. This paper proposes a…
We consider online learning in episodic loop-free Markov decision processes (MDPs), where the loss function can change arbitrarily between episodes, and the transition function is not known to the learner. We show…
Deep-learning-based intelligent services have become prevalent in cyber-physical applications including smart cities and health-care. Deploying deep-learning-based intelligence near the end-user enhances privacy protection, responsiveness,…
We study an online joint assortment-inventory optimization problem, in which we assume that the choice behavior of each customer follows the Multinomial Logit (MNL) choice model, and the attraction parameters are unknown a priori. The…
Towards safe autonomous driving (AD), we consider the problem of learning models that accurately capture the diversity and tail quantiles of human driver behavior probability distributions, in interaction with an AD vehicle. Such models,…
Learning-to-defer (L2D) routes each decision to a system's own predictor or to an external expert. Streaming time-series settings break the offline-L2D assumptions: the data are non-stationary, expert availability shifts over time, and the…