New algorithms optimize algorithm parameters in online settings with reduced computational costs.
problem Optimizing algorithm parameters in online settings with volatile and discontinuous losses.
method Developed semi-bandit optimization algorithms that leverage extra information to reduce computational costs.
result Achieved regret bounds as good as full-information feedback with significantly less computational effort.
Transforms offline greedy algorithms to online algorithms for combinatorial problems.
problem Online decision-making in time-varying combinatorial environments.
method General framework using Blackwell approachability and Bandit Blackwell approachability.
result Achieves O ( T ) O(\sqrt{T}) O ( T ) regret in full information setting and O ( T 2 / 3 ) O(T^{2/3}) O ( T 2/3 ) regret in bandit setting. New algorithm learns optimal ad pricing in online advertising.
problem Optimizing ad pricing in a waterfall system.
method Online learning algorithm interleaves learning and optimization.
result Sublinear regret compared to traditional methods.
Optimized algorithms for online learning with linear constraints improve performance and provide worst-case analysis.
problem Improving online learning algorithms for constrained optimization problems.
method Developed an optimized variant of an online Frank-Wolfe algorithm and used semidefinite programming for numerical analysis.
result No pure online Frank-Wolfe algorithm can have a better regret guarantee than O(T^3/4) without additional assumptions.
We study the task of online boosting--combining online weak learners into an online strong learner. While batch boosting has a sound theoretical foundation, online boosting deserves more study from the theoretical perspective. In this paper, we carefully compare the differences between online and batch boosting, and pr…
This work establishes always-valid risk bounds for online matrix completion.
problem Challenges in establishing always-valid concentration inequalities for online matrix completion.
method Combines non-asymptotic martingale concentration and regularized low-rank matrix regression.
result Establishes always-valid risk bound process for online matrix completion.
In this paper, we design a nonparametric online algorithm for estimating the triggering functions of multivariate Hawkes processes. Unlike parametric estimation, where evolutionary dynamics can be exploited for fast computation of the gradient, and unlike typical function learning, where representer theorem is readily …
Designs an online selective sampling approach for choosing which model to use.
problem Active model selection for pre-trained classifiers in unlabeled data streams.
method Online selective sampling approach to query and label examples.
result High probability of outputting the best model with minimal label queries.
New approach for algorithms that learn predictors to improve performance.
problem Improving algorithm performance by learning better predictions.
method Identify functional dependence and apply online learning techniques.
result Improved results in various online settings with simpler analysis.
As an emerging research direction, online streaming feature selection deals with sequentially added dimensions in a feature space while the number of data instances is fixed. Online streaming feature selection provides a new, complementary algorithmic methodology to enrich online feature selection, especially targets t…
AUC (Area under the ROC curve) is an important performance measure for applications where the data is highly imbalanced. Learning to maximize AUC performance is thus an important research problem. Using a max-margin based surrogate loss function, AUC optimization problem can be approximated as a pairwise rankSVM learni…
OOMP selects features online for sparse linear regression.
problem Feature selection in high-dimensional sparse linear models.
method Online algorithm that alternates between feature selection and coefficient estimation.
result Theoretical guarantees and computational complexity analysis of OOMP.
Efficient strategies for online learning against bandit algorithms solve minimax problems.
problem Solving min-max problems in convex-linear settings with empirical distributions.
method Designing online learning algorithms that play against bandit algorithms, leveraging properties of the set of empirical distributions.
result High-probability convergence guarantees to minimax values for a specific family of sets.
New RL approach learns dynamic VCG mechanisms in unknown MDP environments.
problem Learning dynamic VCG mechanisms in unknown MDP environments.
method Reward-free online RL for exploration, combined with function approximation.
result Regret bound of O ~ ( T 2 / 3 ) \tilde{\mathcal{O}}(T^{2/3}) O ~ ( T 2/3 ) for dynamic VCG mechanism learning. Algorithm provides online learning guarantees against general comparators in full and bandit feedback.
problem Adversarial online learning with data-dependent regret guarantees.
method Completely online algorithm with data-dependent regret guarantees for full and bandit feedback.
result Algorithm achieves expected performance against arbitrary comparator sequences in full and bandit feedback settings.
Improved resource allocation method reduces procurement costs.
problem Online resource allocation with procurement costs.
method Primal-dual algorithm with surrogate function optimization.
result Enhanced competitive ratio through design methods.
Comparison Lift uses bandit algorithms to optimize online ad testing.
problem Optimizing online ad testing to maximize click-through rates.
method Bandit-based experimentation algorithm that adapts to test results.
result Ad click-through rates increased by 46% on average.
Online learning algorithms have impressive convergence properties when it comes to risk minimization and convex games on very large problems. However, they are inherently sequential in their design which prevents them from taking advantage of modern multi-core architectures. In this paper we prove that online learning …
The paper proposes calibration to improve algorithm performance using machine learning predictions.
problem Improving real-world performance of online algorithms with machine learning predictions.
method Calibration as a tool to bridge the gap between prediction uncertainty and algorithm design.
result Calibrated advice leads to more effective guidance in high-variance settings and significant performance improvements in real-world data.
New algorithm improves online binary classification with constant time complexity.
problem Online binary classification with rebalancing.
method Non-iteratively reweighted recursive least-squares.
result Exacts converges to batch formulation and outperforms existing algorithms.
Paper studies continuous prediction with experts' advice using differential equations.
problem Continuous prediction with experts' advice in online learning.
method Continuous-time stochastic calculus and differential equations.
result Improved guarantees for quantile regret with continuous-time algorithm.
New machine learning algorithms inspired by ecological principles.
problem Improving machine learning performance.
method Inspired by ecological dynamics, developed new online SVM algorithms.
result New algorithms outperform traditional methods on the MNIST dataset.
New algorithm handles bandit problems under translations and scales.
problem Adversarial multi-armed bandit problems with arbitrary translations and scales.
method Innovative online algorithm invariant to translations and scales, using universal prediction.
result Second-order regret bounds, unaffected by affine transformations of losses.
Universal algorithm for online convex optimization with optimal regret bounds.
problem Designing a universal algorithm for online convex optimization that works for multiple types of loss functions.
method Maler algorithm: runs multiple learning algorithms in parallel and selects the best one.
result Achieves optimal regret bounds for general convex, exponentially concave, and strongly convex functions.
New algorithm uses imperfect advice to improve online bipartite matching performance.
problem Online bipartite matching with imperfect advice.
method Designing an algorithm that uses external advice to improve performance between advice-free methods and optimal ratio.
result Algorithm achieves competitive ratio interpolating between advice-free methods and optimal ratio of 1.
User engagement in social networks depends critically on the number of online actions their users take in the network. Can we design an algorithm that finds when to incentivize users to take actions to maximize the overall activity in a social network? In this paper, we model the number of online actions over time usin…
Online learning algorithms are designed to learn even when their input is generated by an adversary. The widely-accepted formal definition of an online algorithm's ability to learn is the game-theoretic notion of regret. We argue that the standard definition of regret becomes inadequate if the adversary is allowed to a…
We consider the multi-label ranking approach to multi-label learning. Boosting is a natural method for multi-label ranking as it aggregates weak predictions through majority votes, which can be directly used as scores to produce a ranking of the labels. We design online boosting algorithms with provable loss bounds for…
Adaptive and sequential experiment design is a well-studied area in numerous domains. We survey and synthesize the work of the online statistical learning paradigm referred to as multi-armed bandits integrating the existing research as a resource for a certain class of online experiments. We first explore the tradition…
Study of online learning for structured prediction problems.
problem Structured prediction in online learning settings.
method Developed algorithms for structured prediction in online learning, generalizing from supervised learning.
result Achieved the same excess risk upper bound for non-i.i.d. data and bounded the stochastic regret for non-stationary data.
Paper addresses private online convex optimization with optimal algorithms in various geometries and high-dimensional bandits.
problem Private online convex optimization with streaming and continual release data.
method Proposes a private variant of online Frank-Wolfe algorithm with recursive gradients for variance reduction.
result Achieves optimal excess risk in linear time for 1 < p ≤ 2 1<p\leq 2 1 < p ≤ 2 and state-of-the-art excess risk for 2 < p ≤ ∞ 2<p\leq\infty 2 < p ≤ ∞ . Avare improves optimization and sampling with adaptive importance sampling.
problem Improving convergence rate of stochastic gradient-based algorithms.
method Adaptive importance sampling with decreasing step-sizes.
result Achieves dynamic regret bounds of O ( T 2 / 3 ) \mathcal{O}(T^{2/3}) O ( T 2/3 ) and O ( T 5 / 6 ) \mathcal{O}(T^{5/6}) O ( T 5/6 ) . New algorithm reduces decision switching in dynamic environments.
problem Online learning with memory and non-stationary environments.
method Dynamic policy regret, novel ensemble approach, meta-base decomposition.
result Proves optimal dynamic policy regret for memory length, non-stationarity, and time horizon.
Banker-OMD improves online learning with delayed feedback.
problem Handling delayed feedback in online learning.
method Generalized Online Mirror Descent (OMD) framework.
result Achieves nearly-optimal performance in three bandit scenarios.
We consider the problem of online linear regression on arbitrary deterministic sequences when the ambient dimension d can be much larger than the number of time rounds T. We introduce the notion of sparsity regret bound, which is a deterministic online counterpart of recent risk bounds derived in the stochastic setting…
Study shows online learning algorithms incentivize low-quality content, proposing new algorithms to improve quality.
problem Online learning algorithms in content recommender systems incentivize producers to create low-quality content.
method Analyzed the game between producers and content quality, designed new learning algorithms to incentivize high effort and quality.
result New algorithms incentivize producers to invest high effort and achieve high user welfare, improving content quality.
The paper develops a new algorithm for constructing minimax estimators using online learning techniques.
problem Designing minimax estimators for probability distribution parameters.
method Viewing the problem as a zero-sum game and using online learning with non-convex losses to find a Nash equilibrium.
result The algorithm constructs both a minimax estimator and a least favorable prior.
New algorithms reduce regret in online learning with imperfect hints.
problem Designing algorithms to minimize regret in online learning with imperfect hints.
method Developed algorithms that are resilient to bad hints and interpolate between correlated and no-hints cases.
result Achieved nearly matching lower bounds for online learning with imperfect directional hints.
AR design reduces multi-armed bandit experiment cost.
problem Comparing multi-armed bandit algorithms requires many restarts.
method Artificial Replay (AR) design for bandit experiments.
result AR reduces experimental cost by requiring only T + o ( T ) T + o(T) T + o ( T ) user interactions. This paper bridges offline and online RL by studying policy finetuning with a reference policy.
problem Sample-efficient reinforcement learning in online and offline settings.
method Design of policy finetuning algorithms and analysis of sample complexity.
result Theoretical analysis shows that the optimal policy finetuning algorithm is either offline reduction or purely online RL.
Paper tackles online allocation problems using adversarial training.
problem Online bipartite matching, especially in AdWords.
method Constructs a framework combining game theory, adversarial training, and GANs.
result Designs robust algorithms that perform well under practical and adversarial conditions.
New online GP algorithm offers performance guarantees for streaming data.
problem Training and inference of GPs require all historic data, limiting online decision-making.
method Developed a new theoretical framework based on PAC-Bayes theory, optimizing empirical risk and parameter divergence.
result Offers both a guarantee of generalized performance and good accuracy.
New algorithm predicts piecewise regular functions online.
problem Online prediction of piecewise regular functions.
method Modified sleeping experts aggregation algorithm.
result Oracle risk bounds for all local regions.
Unified framework for analyzing online convex optimization across various settings.
problem Analyzing online convex optimization in different settings and feedback types.
method Unified framework allowing systematic proposal and analysis of meta-algorithms.
result Comparable regret bounds for various feedback types and adversary types.
New algorithms reduce dynamic regret in online MDPs with changing losses.
problem Online MDPs with adversarial loss changes and known transitions.
method Dynamic regret measure, novel ensemble algorithms for three models.
result Provably optimal dynamic regret bounds for episodic SSP, improved bounds for predictable environments.
Algorithm reduces online regret by leveraging offline data in linear bandits.
problem Online regret minimization in linear bandits with offline data.
method OOPE algorithm using extended D-optimal design.
result Substantial reduction in online regret compared to prior work.
Improved online classification with accurate predictions.
problem Online classification challenges with limited data.
method Designing an online learner that uses predictions to reduce regret.
result Expected regret is better than worst-case analysis, especially with accurate predictions.
New DP algorithms achieve near-optimal regret bounds for online learning problems.
problem Online learning problems with zero-loss solutions and differential privacy constraints.
method Developed new Differentially Private algorithms with near-optimal regret bounds.
result Achieved near-optimal regret bounds for various online prediction and convex optimization problems.