arXiv research

Fast algorithms developed for adaptive and fully adaptive submodular maximization problems.

We propose a new image denoising algorithm, dubbed as Fully Convolutional Adaptive Image DEnoiser (FC-AIDE), that can learn from an offline supervised training set with a fully convolutional neural network as well as adaptively fine-tune the supervised model for each given noisy image. We significantly extend the frame…

Improved elimination strategies for adaptive bandit identification reduce sample complexity and computational burden.

Paper analyzes convergence rates for multi-agent learning in games.

We propose the first fully-adaptive algorithm for pure exploration in linear bandits---the task to find the arm with the largest expected reward, which depends on an unknown parameter linearly. While existing methods partially or entirely fix sequences of arm selections before observing rewards, our method adaptively c…

New filters match advanced composition for adaptive privacy, with practical constants.

A decentralized approach for multi-source domain adaptation.

Alpha-trimming prunes trees in random forests to improve predictive performance.

Given a mixture between two populations of coins, "positive" coins that each have -- unknown and potentially different -- bias $\geq\frac{1}{2}+Δ$ and "negative" coins with bias $\leq\frac{1}{2}-Δ$, we consider the task of estimating the fraction $ρ$ of positive coins to within additive error $ε$. We achieve an upper a…

We take initial steps in studying PAC-MDP algorithms with limited adaptivity, that is, algorithms that change its exploration policy as infrequently as possible during regret minimization. This is motivated by the difficulty of running fully adaptive algorithms in real-world applications (such as medical domains), and …

Convolutional nets require fewer samples than fully-connected nets for image classification.

Unified framework for analyzing online convex optimization across various settings.

New algorithm achieves near-optimal performance in dueling bandit problem.

Adversarial examples are a pervasive phenomenon of machine learning models where seemingly imperceptible perturbations to the input lead to misclassifications for otherwise statistically accurate models. In this paper we study how the choice of optimization algorithm influences the robustness of the resulting classifie…

New algorithm tackles nonconvex machine learning problems with adaptive normalization and independent sampling.

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

Algorithm estimates principal eigenvector with adaptive sensing, improving over non-adaptive methods.

TiAda adapts adaptive gradient methods for nonconvex minimax optimization.

New algorithm maximizes non-monotone adaptive submodular functions in linear time.

New algorithm reduces interventional strategy complexity for causal graph discovery.

Paper tackles test-time adaptation for tabular data.

Adaptive algorithms minimize regret in matching markets with contextual arm preferences.

Adaptive algorithm improves nonlinear data assimilation for non-Gaussian systems.

Paper tackles adaptive deletion of data points from trained models.

We propose an adaptive smoothing algorithm based on Nesterov's smoothing technique in \cite{Nesterov2005c} for solving "fully" nonsmooth composite convex optimization problems. Our method combines both Nesterov's accelerated proximal gradient scheme and a new homotopy strategy for smoothness parameter. By an appropriat…

Extends DRFGP to make GPs more robust and adaptive for dynamic, noisy data.

Recently, a number of mostly $\ell_1$-norm regularized least squares type deterministic algorithms have been proposed to address the problem of \emph{sparse} adaptive signal estimation and system identification. From a Bayesian perspective, this task is equivalent to maximum a posteriori probability estimation under a …

Recent literature on online learning has focused on developing adaptive algorithms that take advantage of a regularity of the sequence of observations, yet retain worst-case performance guarantees. A complementary direction is to develop prediction methods that perform well against complex benchmarks. In this paper, we…

Major internet companies routinely perform tens of thousands of A/B tests each year. Such large-scale sequential experimentation has resulted in a recent spurt of new algorithms that can provably control the false discovery rate (FDR) in a fully online fashion. However, current state-of-the-art adaptive algorithms can …

Tent adapts models during testing by minimizing entropy of predictions.

New algorithms reduce online learning regret by tracking gradient variation.

Proposes a new algorithm for solving optimization problems with stochastic objectives and equality constraints.

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…

Discriminative clustering learns from both labeled and unlabeled data.

The clusters of a distribution are often defined by the connected components of a density level set. However, this definition depends on the user-specified level. We address this issue by proposing a simple, generic algorithm, which uses an almost arbitrary level set estimator to estimate the smallest level at which th…

Bayesian adaptive PCE method improves surrogate modeling and sensitivity analysis.

Efficient algorithms for contextual slate bandits with limited adaptivity.

We give a new algorithm for best arm identification in linearly parameterised bandits in the fixed confidence setting. The algorithm generalises the well-known LUCB algorithm of Kalyanakrishnan et al. (2012) by playing an arm which minimises a suitable notion of geometric overlap of the statistical confidence set for t…

The computational costs of inference and planning have confined Bayesian model-based reinforcement learning to one of two dismal fates: powerful Bayes-adaptive planning but only for simplistic models, or powerful, Bayesian non-parametric models but using simple, myopic planning strategies such as Thompson sampling. We …

Transductive Adversarial Networks (TAN) is a novel domain-adaptation machine learning framework that is designed for learning a conditional probability distribution on unlabelled input data in a target domain, while also only having access to: (1) easily obtained labelled data from a related source domain, which may ha…

Adaptive learning, also known as adaptive teaching, relies on learning path recommendation, which sequentially recommends personalized learning items (e.g., lectures, exercises) to satisfy the unique needs of each learner. Although it is well known that modeling the cognitive structure including knowledge level of lear…

Localizes curvature estimates for evolving hypersurfaces under various flows.

We address the issue of speeding up the training of convolutional neural networks by studying a distributed method adapted to stochastic gradient descent. Our parallel optimization setup uses several threads, each applying individual gradient descents on a local variable. We propose a new way of sharing information bet…

Adaptive classification methods ensure correct prediction intervals.

An algorithm learns from multiple models to match an oracle's risk.

Paper develops new algorithms for unsupervised multi-class domain adaptation.

Variational Bayesian neural nets combine the flexibility of deep learning with Bayesian uncertainty estimation. Unfortunately, there is a tradeoff between cheap but simple variational families (e.g.~fully factorized) or expensive and complicated inference procedures. We show that natural gradient ascent with adaptive w…

Paper studies competitive networks where teams aim to minimize their own objectives, adapting to each other's strategies.