arXiv research

New bounds show simple predictors can learn complex concepts online.

Post-processing predictors reduces calibration errors for decision-making.

FOLKLORE algorithm speeds up online multiclass logistic regression.

Learning linear predictors with the logistic loss---both in stochastic and online settings---is a fundamental task in machine learning and statistics, with direct connections to classification and boosting. Existing "fast rates" for this setting exhibit exponential dependence on the predictor norm, and Hazan et al. (20…

Study predicts online procrastination using machine learning.

Study shows NCCP can replace CP for ACI in non-exchangeable data.

Bayesian framework reduces online optimization regret.

In this work, we study the problem of aggregating a finite number of predictors for nonstationary sub-linear processes. We provide oracle inequalities relying essentially on three ingredients: (1) a uniform bound of the $\ell^1$ norm of the time varying sub-linear coefficients, (2) a Lipschitz assumption on the predict…

Simple algorithm achieves distance to calibration error of at most 2√T+1.

MELO predicts electricity loads by adapting to shifts without external indicators.

New approach for algorithms that learn predictors to improve performance.

We study online linear regression problems in a distributed setting, where the data is spread over a network. In each round, each network node proposes a linear predictor, with the objective of fitting the \emph{network-wide} data. It then updates its predictor for the next round according to the received local feedbac…

New method minimizes regret in AMDP with high probability.

This paper tackles continuous covariate shift by adaptively training predictors.

Study shows sample complexity for multicalibration is Θ(ε^-3) with polylogarithmic factors.

Paper develops a discounted algorithm for online convex optimization that adapts to unknown discount factors.

Study online linear regression with paid noise reduction.

Optimizes predictions by recalibrating online forecasts with minimal error.

We propose a novel nonparametric online predictor for discrete labels conditioned on multivariate continuous features. The predictor is based on a feature space discretization induced by a full-fledged k-d tree with randomly picked directions and a recursive Bayesian distribution, which allows to automatically learn th…

We study the interplay between sequential decision making and avoiding discrimination against protected groups, when examples arrive online and do not follow distributional assumptions. We consider the most basic extension of classical online learning: "Given a class of predictors that are individually non-discriminato…

Solves online 3D bin packing with deep reinforcement learning under constraints.

Online distributional prediction with latent cluster geometry

We develop an online learning method for prediction, which is important in problems with large and/or streaming data sets. We formulate the learning approach using a covariance-fitting methodology, and show that the resulting predictor has desirable computational and distribution-free properties: It is implemented onli…

We introduce a recursive adaptive group lasso algorithm for real-time penalized least squares prediction that produces a time sequence of optimal sparse predictor coefficient vectors. At each time index the proposed algorithm computes an exact update of the optimal $\ell_{1,\infty}$-penalized recursive least squares (R…

This research improves online learning by correcting for target shift in machine learning.

Financial market prediction on the basis of online sentiment tracking has drawn a lot of attention recently. However, most results in this emerging domain rely on a unique, particular combination of data sets and sentiment tracking tools. This makes it difficult to disambiguate measurement and instrument effects from f…

We present a predictor-corrector framework, called PicCoLO, that can transform a first-order model-free reinforcement or imitation learning algorithm into a new hybrid method that leverages predictive models to accelerate policy learning. The new "PicCoLOed" algorithm optimizes a policy by recursively repeating two ste…

Paper develops an online learning algorithm for functional data models.

New algorithms achieve better regret bounds for online classification with relaxed benchmarks.

We study online prediction of bounded stationary ergodic processes. To do so, we consider the setting of prediction of individual sequences and build a deterministic regression tree that performs asymptotically as well as the best L-Lipschitz constant predictors. Then, we show why the obtained regret bound entails the …

The study simplifies assessing overlap in logistic regression models using empirical likelihood.

Data driven soft sensor design has recently gained immense popularity, due to advances in sensory devices, and a growing interest in data mining. While partial least squares (PLS) is traditionally used in the process literature for designing soft sensors, the statistical literature has focused on sparse learners, such …

We investigate online classification with paid stochastic experts. Here, before making their prediction, each expert must be paid. The amount that we pay each expert directly influences the accuracy of their prediction through some unknown Lipschitz "productivity" function. In each round, the learner must decide how mu…

New algorithm reduces online learning error for unknown feature distributions.

The paper explores trade-offs between regret and variance in online learning algorithms.

Characterizes statistical complexity of realizable regression in PAC and online learning.

The paper proposes calibration to improve algorithm performance using machine learning predictions.

SA algorithms control dynamic regret in non-stationary settings with strong convexity or exp-concavity.

New algorithm provides robust uncertainty quantification without parameter tuning.

We study the problem of estimating the parameters of a regression model from a set of observations, each consisting of a response and a predictor. The response is assumed to be related to the predictor via a regression model of unknown parameters. Often, in such models the parameters to be estimated are assumed to be c…

Paper achieves logarithmic regret for online Kalman filter learning.

Study selective classification with limited feedback in online learning.

A scalable GP model for online uncertainty quantification over graphs.

Study uses multiple online media to predict crude oil prices.

Improves multi-objective learning by adapting to local subintervals.

We study online prediction where regret of the algorithm is measured against a benchmark defined via evolving constraints. This framework captures online prediction on graphs, as well as other prediction problems with combinatorial structure. A key aspect here is that finding the optimal benchmark predictor (even in hi…

In online advertising, display ads are increasingly being placed based on real-time auctions where the advertiser who wins gets to serve the ad. This is called real-time bidding (RTB). In RTB, auctions have very tight time constraints on the order of 100ms. Therefore mechanisms for bidding intelligently such as clickth…

Unified online tensor learning algorithm reduces computational and memory costs.