arXiv research

New technique for multiple-source adaptation without density estimation.

Adaptive method improves numerical solution of Cox-Ingersoll-Ross model.

A nonlinear wave alternative for the standard Black-Scholes option-pricing model is presented. The adaptive-wave model, representing 'controlled Brownian behavior' of financial markets, is formally defined by adaptive nonlinear Schrödinger (NLS) equations, defining the option-pricing wave function in terms of the stock…

Adaptive optimization methods, which perform local optimization with a metric constructed from the history of iterates, are becoming increasingly popular for training deep neural networks. Examples include AdaGrad, RMSProp, and Adam. We show that for simple overparameterized problems, adaptive methods often find drasti…

Adaptive learning of SPDE solutions using score-based diffusion models.

We consider the optimal solutions to the trade execution problem in the two different classes of i) fully adapted or adaptive and ii) deterministic or static strategies, comparing them. We do this in two different benchmark models. The first model is a discrete time framework with an information flow process, dealing w…

Enhances physics-informed neural networks with adaptive sampling and weighting.

Improved iterative hard thresholding for faster, sparser solutions.

This paper explores adaptive methods in over-parameterized linear regression.

Self-adaptive PINNs improve accuracy in stiff PDEs.

This work includes a number of novel contributions for the multiple-source adaptation problem. We present new normalized solutions with strong theoretical guarantees for the cross-entropy loss and other similar losses. We also provide new guarantees that hold in the case where the conditional probabilities for the sour…

CoLoRA models predict PDE solutions quickly and accurately with minimal data.

Local adaptive methods in FL can accelerate convergence but introduce bias, which is corrected.

Adaptive methods produce less robust models to adversarial examples.

Proposes MEDM to balance entropy minimization and diversity maximization for better domain adaptation.

Study improves domain adaptation with limited labeled data.

Paper proposes efficient algorithms for bandit problems with costly sampling.

Study on generalization in gradient-based meta-learning, showing flatter solutions and coherence between adaptation trajectories.

In this paper is proposed a new heuristic approach belonging to the field of evolutionary Estimation of Distribution Algorithms (EDAs). EDAs builds a probability model and a set of solutions is sampled from the model which characterizes the distribution of such solutions. The main framework of the proposed method is an…

A new adaptive splitting method improves accuracy for Cox-Ingersoll-Ross model.

Adaptive Bayesian learning agent for non-stationary bandits.

Prodigy estimates learning rate without tuning, improving convergence.

AgABC improves ABC algorithm by balancing exploration and exploitation.

Adaptive SAA solves large-scale stochastic linear programs efficiently.

Optimizes staggered treatment rollouts to minimize cost and error.

An adaptive dropout approach improves high-dimensional Bayesian optimization.

Adapts PALM to solve NMF with smooth and sparse solutions.

Minimax optimization plays a key role in adversarial training of machine learning algorithms, such as learning generative models, domain adaptation, privacy preservation, and robust learning. In this paper, we demonstrate the failure of alternating gradient descent in minimax optimization problems due to the discontinu…

Proposes a regularization method for unsupervised domain adaptation that aligns predictions with target data's top singular vectors.

Chameleon optimizes neural network compilation for faster execution and shorter time.

Paper develops methods for solving complex stochastic equations using Malliavin calculus.

Study adaptive clinical trial methods for identifying patient subpopulations with treatment benefit.

Derives Li & Yau estimates for heat equations on manifolds.

New method learns diverse solutions in reinforcement learning without gradient bias.

Adaptive PINNs improve accuracy by adding points where solutions are uncertain.

The problem of spoofing attacks is increasingly relevant as digital systems are becoming more ubiquitous. Thus the detection of such attacks and the localisation of attackers have been objects of recent study. After an attack has been detected, various algorithms have been proposed in order to localise the attacker. In…

Paper analyzes adaptive ISTA with MAD for LASSO problem.

This paper provides a theoretical analysis of domain adaptation based on the PAC-Bayesian theory. We propose an improvement of the previous domain adaptation bound obtained by Germain et al. in two ways. We first give another generalization bound tighter and easier to interpret. Moreover, we provide a new analysis of t…

The paper examines how sampling data affects the performance of submodular maximization.

Modeling bone microarchitecture adaptation using geometric flows.

CMA-ME combines CMA-ES and MAP-Elites for better quality and diversity in continuous domains.

Online learners track optimal solutions with constant step-size.

In this study, we focus on the market clearing problem of Turkish day-ahead electricity market. We propose a mathematical model by extending the variety of bid types for different price regions. The commercial solvers may not find any feasible solution for the proposed problem in some instances within the given time li…

MAML outperforms NAL in diverse task landscapes.

Achieving faster execution with shorter compilation time can enable further diversity and innovation in neural networks. However, the current paradigm of executing neural networks either relies on hand-optimized libraries, traditional compilation heuristics, or very recently, simulated annealing and genetic algorithms.…

Adaptive multi-domain learning reduces parameter count for efficient deep learning.

AdaPTS adapts univariate FMs for multivariate time series forecasting.

New method combines Bloom filters and belief propagation for efficient group testing.