arXiv research

Study analyzes deep learning's performance on variable exponent Besov space, highlighting adaptivity benefits.

Data-driven method for error estimation without needing class complexity.

Quantized Adam reduces communication cost in deep learning training.

Adapts RKHS methods to estimate density ratios with optimal error.

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

The paper tackles gradual domain adaptation with manifold-constrained DRO, showing error bounds across distributions.

LALR adapts learning rate for faster convergence in regression and neural nets.

In recent years, correntropy has been seccessfully applied to robust adaptive filtering to eliminate adverse effects of impulsive noises or outliers. Correntropy is generally defined as the expectation of a Gaussian kernel between two random variables. This definition is reasonable when the error between the two random…

In this work, we present a novel upper bound of target error to address the problem for unsupervised domain adaptation. Recent studies reveal that a deep neural network can learn transferable features which generalize well to novel tasks. Furthermore, a theory proposed by Ben-David et al. (2010) provides a upper bound …

Adaptive importance samplers are adaptive Monte Carlo algorithms to estimate expectations with respect to some target distribution which \textit{adapt} themselves to obtain better estimators over a sequence of iterations. Although it is straightforward to show that they have the same $\mathcal{O}(1/\sqrt{N})$ convergen…

Network agents solve adaptive regression problems with compressed signals.

Paper proposes adaptive parameter selection for KGD algorithms.

Paper adapts ACI for online multi-step time-series forecasting with coverage guarantees.

Calibrated probabilistic solvers improve accuracy of ODE estimates.

This paper addresses the robust speech recognition problem as an adaptation task. Specifically, we investigate the cumulative application of adaptation methods. A bidirectional Long Short-Term Memory (BLSTM) based neural network, capable of learning temporal relationships and translation invariant representations, is u…

VCoTTA uses variational Bayesian methods to adapt models under continuous domain shifts.

Adapts Neyman-Pearson classification for both source and target distribution shifts.

Supporting evidence for adaptive feature program across diverse models.

Tent adapts models during testing by minimizing entropy of predictions.

Adaptive distributed SGD reduces delay in slow workers.

New insights into variable selection with different model assumptions.

Improves ASR accuracy for domain mismatch using machine translation.

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…

LoRA enhances model adaptability without increasing parameters.

Selective state-adaptive regularization improves offline RL performance.

New algorithm learns changing discrete distributions with minimal drift error.

Robust diffusion adaptive estimation algorithms based on the maximum correntropy criterion (MCC), including adaptation to combination MCC and combination to adaptation MCC, are developed to deal with the distributed estimation over network in impulsive (long-tailed) noise environments. The cost functions used in distri…

Self-training improves gradual domain adaptation with unlabeled data.

New robust estimator improves variable selection and coefficient estimation in linear regression with heavy-tailed errors and outliers.

Adaptive PCR improves panel data analysis with uniform guarantees.

New framework tackles multi-source domain adaptation with optimism and consistency.

Sequential Kernel-based Conditional Independence Testing via Adaptive Betting

Due to the ability of deep neural nets to learn rich representations, recent advances in unsupervised domain adaptation have focused on learning domain-invariant features that achieve a small error on the source domain. The hope is that the learnt representation, together with the hypothesis learnt from the source doma…

New method uses online learning to improve AIPW estimators for adaptively collected data.

The paper analyzes sparse high-dimensional linear regression with random design and unknown error variance, providing adaptiveness and concentration rates.

A new data-adaptive prior stabilizes kernel learning in operators.

Method aggregates models with different hyper-parameters to adapt to target domain.

Latent FxLMS accelerates ANC by adapting along low-dimensional filter weights.

Transfer Learning (TL) in Deep Neural Networks is gaining importance because in most of the applications, the labeling of data is costly and time-consuming. Additionally, TL also provides an effective weight initialization strategy for Deep Neural Networks . This paper introduces the idea of Adaptive Transfer Learning …

We study the problem of estimating a set of $d$ linear queries with respect to some unknown distribution $\mathbf{p}$ over a domain $\mathcal{J}=[J]$ based on a sensitive data set of $n$ individuals under the constraint of local differential privacy. This problem subsumes a wide range of estimation tasks, e.g., distrib…

Adaptive algorithm identifies best arm with abstention, showing phase transition from polynomial to exponential error probability.

New algorithm for adaptive experimental design in scientific settings.

Introduces Cauchy-Schwarz divergence for domain adaptation.

New algorithms adaptively calibrate predictions in non-stationary environments, matching optimal rates.

The study analyzes transfer learning using information theory.

Artificial neural network training with stochastic gradient descent can be destabilized by "bad batches" with high losses. This is often problematic for training with small batch sizes, high order loss functions or unstably high learning rates. To stabilize learning, we have developed adaptive learning rate clipping (A…

Adaptive learning method for stochastic programs with latent uncertainty.

New method controls false discoveries in real-time data streams.