Study on computable online learning with new conditions and complexities.
problem Characterizing optimal online learning under varying optimality requirements.
method Introduced anytime optimal (a-optimal) online learning and explored computational separations.
result Found a computational separation between a-optimal and optimal online learning.
This paper presents competitive algorithms for a novel class of online optimization problems with memory. We consider a setting where the learner seeks to minimize the sum of a hitting cost and a switching cost that depends on the previous p p p decisions. This setting generalizes Smoothed Online Convex Optimization. The…
Boosting improves online decision-making for large expert sets.
problem Online convex optimization with many experts is infeasible.
method Generalizes online boosting to online convex optimization and bandit linear optimization settings.
result Near-optimal regret guarantees for various feedback models.
New control methods for systems with adversarial perturbations.
problem Control systems with adversarial noise.
method Online convex optimization and convex relaxations.
result Low regret policies against adversarial perturbations.
We introduce several new black-box reductions that significantly improve the design of adaptive and parameter-free online learning algorithms by simplifying analysis, improving regret guarantees, and sometimes even improving runtime. We reduce parameter-free online learning to online exp-concave optimization, we reduce…
New framework uses tempered optimism to handle imperfect experts in online learning.
problem Challenges of implicit optimism in practical online learning environments.
method Introduces tempered optimism as a framework for online non-convex learning, modifies existing algorithms.
result Demonstrates tempered optimism as a fruitful paradigm for online non-convex learning.
New approach for distributed online optimization of non-convex losses with sublinear regret.
problem Regret evaluation and consensus in distributed, multi-agent systems with non-convex losses.
method Composite regret metric and consensus-based online normalized gradient (CONGD) approach for pseudo-convex losses; offline optimization oracle for general non-convex losses.
result First sublinear regret bound for general distributed online non-convex learning.
Extends boosting to multiclass online agnostic classification.
problem Online multiclass classification with weak learners.
method Reduces multiclass online agnostic boosting to online convex optimization.
result First boosting algorithm for online agnostic multiclass classification.
Boosts weak online learners to strong ones with sublinear regret.
problem Online learning agnostic setting without strong guarantees.
method Reduction to online convex optimization, boosting via marginally-better-than-trivial regret guarantees.
result First agnostic online boosting algorithm with sublinear regret.
Proposes OBS, a method to adaptively combine Bayesian models online.
problem Learning optimal combinations of Bayesian models in online learning.
method Empirical Bayes lens, Online Bayesian Stacking (OBS).
result Establishes a novel connection between OBS and portfolio selection.
Continuous-time algorithms improve online learning performance.
problem Online learning with sequential data and minimizing overall regret.
method Extending discrete-time algorithms to continuous-time models for online linear optimization, adversarial bandit, and adversarial linear bandit.
result Optimal regret bounds are proven for continuous-time settings.
New private algorithms for online learning improve regret in high privacy regimes.
problem Private online learning from experts and convex optimization.
method Transformed lazy algorithms for differential privacy.
result Improved regret bounds for DP-OPE and DP-OCO.
Paper proposes online optimization for uncertain systems using machine learning and DRO.
problem Optimization of uncertain dynamical systems with distributional uncertainty.
method Combines machine learning with Distributional Robust Optimization (DRO) to handle uncertainty.
result Online solutions with probabilistic regret bounds for uncertain systems.
New algorithms for constrained online optimization with memory and predictions.
problem Control of constrained dynamical systems and scheduling with reconfiguration budgets.
method Proposed algorithms achieving sublinear regret and constraint violation under time-varying constraints, both with and without predictions.
result First algorithms achieving sublinear regret and constraint violation in constrained online optimization with memory.
Develops a method to estimate optimal policy value in online learning.
problem Challenges in evaluating ongoing policies in online learning environments.
method Doubly Robust Interval Estimation (DREAM) method.
result Valid inference on online conditional mean estimator with asymptotically normal distribution.
Study online monotone density estimation with expert aggregation and log-optimal calibration.
problem Online monotone density estimation and log-optimal calibration.
method Proposed two online estimators: Grenander estimator and expert aggregation estimator.
result Online estimators achieve O ( n 1 / 3 ) O(n^{1/3}) O ( n 1/3 ) cumulative log-likelihood gap and n log n \sqrt{n\log{n}} n log n pathwise regret bound. Fast algorithm for online optimization on transport polytopes.
problem Optimizing convex objectives on transport polytopes.
method Mirror Sinkhorn algorithm combining Sinkhorn scaling and mirror descent.
result Robust and efficient online optimization for convex objectives.
Adversarial online nonparametric regression achieves optimal rates with locally adaptive learning.
problem Adversarial online nonparametric regression with general convex losses.
method Parameter-free learning algorithm leveraging chaining trees to compete against H{ö}lder functions, dynamically tracking and adapting to local smoothness variations.
result First computationally efficient algorithm with locally adaptive optimal rates for online regression in an adversarial setting.
New algorithm reduces online hyperparameter optimization costs.
problem High cost of evaluating validation examples in online HPO.
method Modeling online HPO as a time-varying Bayesian optimization problem, proposing a costly feedback setting.
result Cost-efficient GP-UCB algorithm reaches human expert-level performance.
Paper studies a robust online learning algorithm for regression.
problem Develops a robust online learning algorithm for regression problems.
method Introduces an online learning algorithm with a robust loss function over RKHS.
result The algorithm achieves optimal convergence rates in mean square and RKHS.
Bayesian framework reduces online optimization regret.
problem Sequential optimization in dynamic environments with bounded losses.
method PAC-Bayes theory and Bayesian updating principles.
result Achieves O ( T ) \mathcal{O}(\sqrt{T}) O ( T ) regret for bounded losses. In online learning, the dynamic regret metric chooses the reference (optimal) solution that may change over time, while the typical (static) regret metric assumes the reference solution to be constant over the whole time horizon. The dynamic regret metric is particularly interesting for applications such as online reco…
Optimal algorithms for online convex optimization with random order.
problem Online convex optimization with random order and non-convex loss functions.
method Stochastic gradient descent and algorithmic stability analysis.
result Achieves optimal bounds and significantly outperforms previous methods.
A new algorithm reduces online exp-concave optimization runtime.
problem Minimizing regret in online learning with exponentially concave losses.
method LightONS, a variant of Online Newton Step (ONS), reduces runtime to O ( d 2 T + d ω T log T ) O(d^2 T + d^ω\sqrt{T \log T}) O ( d 2 T + d ω T log T ) . result Optimal regret with reduced runtime to O ( d 2 T + d ω T log T ) O(d^2 T + d^ω\sqrt{T \log T}) O ( d 2 T + d ω T log T ) . Optimal bounds on regret and constraint violation in adversarial COCO.
problem Minimizing regret and cumulative constraint violation in adversarial COCO.
method New surrogate loss function and Follow-the-Regularized-Leader/Online Gradient Descent.
result Achieved optimal O ( T ) O(\sqrt{T}) O ( T ) bounds on both regret and cumulative constraint violation. We propose accelerated randomized coordinate descent algorithms for stochastic optimization and online learning. Our algorithms have significantly less per-iteration complexity than the known accelerated gradient algorithms. The proposed algorithms for online learning have better regret performance than the known rando…
Efficient boosting method for regression with limited feedback.
problem Online boosting for regression tasks with noisy multi-point bandit feedback.
method Efficient regret minimization method with online boosting algorithm and projection-free online convex optimization.
result Improved state-of-the-art guarantees in efficiency.
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.
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.
New algorithm for online optimization over symmetric cones, unifying previous methods.
problem Online convex optimization over symmetric cones.
method Symmetric-Cone Multiplicative Weights Update (SCMWU) algorithm.
result SCMWU is a no-regret algorithm.
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.
New algorithms optimize non-smooth, non-convex objectives with improved complexity.
problem Optimizing non-smooth, non-convex stochastic objectives.
method Reduction to online learning, applying optimistic online learning techniques.
result Improved complexity for finding ( δ , ε ) (δ,ε) ( δ , ε ) -stationary points. Unified hybrid RL algorithm improves online RL performance with offline data.
problem Improving reinforcement learning performance with limited online data.
method A unified hybrid RL algorithm combining offline and online data.
result Unified algorithm achieves state-of-the-art results in sub-optimality gap and online learning regret.
Online optimization has been a successful framework for solving large-scale problems under computational constraints and partial information. Current methods for online convex optimization require either a projection or exact gradient computation at each step, both of which can be prohibitively expensive for large-scal…
Optimizes crowdsourced preference-based subjective evaluation with online learning.
problem Large-scale evaluation of generative media using crowdsourcing due to combinatorial explosion.
method Automatic optimization of pair combination selections and evaluation volumes with online learning.
result Optimizes evaluation by reducing pair combinations and allocating optimal evaluation volumes.
We consider Online Convex Optimization (OCO) in the setting where the costs are m m m -strongly convex and the online learner pays a switching cost for changing decisions between rounds. We show that the recently proposed Online Balanced Descent (OBD) algorithm is constant competitive in this setting, with competitive rat…
Universal online optimization for dynamic environments using uniclass prediction.
problem Online optimization in changing environments with dynamic regret.
method Reduces dynamic online optimization to uniclass prediction problem, allowing control over dynamic regret bounds.
result First paper with state-of-the-art dynamic regret guarantees for general convex cost functions.
New method optimizes on curved manifolds without curvature dependence.
problem Curvature-dependent regret in online optimization on Hadamard manifolds.
method Riemannian online gradient descent for h-convex functions.
result Established O ( T ) O(\sqrt{T}) O ( T ) and O ( log ( T ) ) O(\log(T)) O ( log ( T )) regret guarantees, curvature-independent. Efficient RNN algorithm guarantees convergence in online learning.
problem Online nonlinear regression with RNNs.
method First-order training algorithm with convergence guarantee.
result The algorithm converges to optimum network parameters.
Develops parameter-free online mirror descent for optimal dynamic regret.
problem Optimal online linear optimization in unbounded domains.
method Modified online mirror descent framework for parameter-free algorithms.
result First unconstrained online linear optimization achieving optimal dynamic regret.
Proposes an online method for high-dimensional streaming data.
problem Increasing variable dimensions with sample size in online kernel sliced inverse regression.
method Introduces approximate linear dependence condition and dictionary variable sets to address the problem. Transforms into online generalized eigen-decomposition problem and uses stochastic optimization for updates.
result Achieves close performance to batch processing kernel sliced inverse regression.
OMGD algorithm optimizes online convex optimization with switching costs and delayed gradients.
problem Optimizing online convex optimization with switching costs and delayed gradients.
method Proposed an online multiple gradient descent (OMGD) algorithm for quadratic and linear switching costs.
result OMGD achieves optimal dynamic regret in the limited information setting.
Optimizes recommender selection online with D-optimal design.
problem Finding the optimal recommender in online exploration-exploitation.
method Leverages D-optimal design from statistics to maximize information gain.
result Achieves maximum information gain during online exploration.
Kernel interpolation speeds up online Gaussian process updates.
problem Efficiently updating Gaussian process posteriors with new data.
method Structured kernel interpolation for constant-time updates.
result Exact inference maintained with constant-time updates.
New adaptive first-order methods improve on quasi-Newton variants.
problem Designing efficient gradient methods for practical applications.
method Online scaled gradient methods (OSGM) with new adaptive methods OSGM-Best.
result OSGM-Best matches quasi-Newton variants but requires less memory and cheaper iterations.
Study on collaborative vs. non-collaborative online and bandit convex optimization.
problem Minimizing average regret in distributed online and bandit convex optimization.
method Analyzes the impact of collaboration in adaptive and zeroth-order feedback settings.
result Collaboration is beneficial in high-dimensional federated online optimization with limited feedback.
We study online optimization in a setting where an online learner seeks to optimize a per-round hitting cost, which may be non-convex, while incurring a movement cost when changing actions between rounds. We ask: \textit{under what general conditions is it possible for an online learner to leverage predictions of futur…
Paper tackles dynamic label shift in online learning, achieving optimal performance.
problem Adapting to changing class marginals in online supervised and unsupervised learning.
method Develops novel algorithms reducing adaptation to online regression, achieving optimal dynamic regret.
result Achieves superior performance in various online label shift scenarios.