Paper tackles online adaptation to changing label distributions.
problem Adapting machine learning models to changing label distributions in real-world settings.
method Leverages novel analysis to show estimation of expected test loss is possible without true labels. Proposes adaptation algorithms inspired by classical online learning techniques.
result Empirically verified that OGD is particularly effective and robust to various label shift scenarios.
Bayesian method adapts to unknown distribution shifts in online learning.
problem Online learning with unknown and irregular distribution shifts.
method Bayesian inference with change-point detection and beam search.
result Improves adaptation to new data distributions over state-of-the-art methods.
Efficiently estimates online variational learning using importance sampling.
problem Online variational estimation in state-space models.
method Variational approach with Monte Carlo importance sampling.
result Proposed efficient algorithm for streaming data.
Wide and Deep GNN learns from distributed graphs and retrain online.
problem Decentralized graph support changes over time, causing mismatch between training and testing graphs.
method Wide and Deep GNN architecture with distributed online learning.
result Convergence guarantees for online retraining of the wide part of the GNN.
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.
Transfer learning has been demonstrated to be successful and essential in diverse applications, which transfers knowledge from related but different source domains to the target domain. Online transfer learning(OTL) is a more challenging problem where the target data arrive in an online manner. Most OTL methods combine…
Anchor-TS uses median anchoring to improve online decision-making from offline data with distribution shift.
problem Improving online decision-making from offline data with distribution shift.
method Sample-Mean Anchored Thompson Sampling (Anchor-TS) with median anchoring.
result Anchor-TS safely leverages offline data to accelerate online learning and reduces regret.
New algorithm for online meta-learning with task boundary detection.
problem Adapting to new tasks in a non-stationary environment.
method Two detection mechanisms for task switches and distribution shift; online model updates based on current data.
result Achieves sublinear task-averaged regret under mild conditions.
The paper provides bounds on estimation error in a distributed online learning setting.
problem Estimating an unknown parameter in a distributed and online manner with finite sample guarantees.
method Proposes a distributed online estimation algorithm that improves accuracy through communication, providing non-asymptotic bounds on estimation error.
result Demonstrates a trade-off between estimation error and communication costs, and determines a stopping time for communication based on desired accuracy.
Algorithm improves online learning in adversarial bandits.
problem Online learning in adversarial multi-armed bandits with non-uniform best arm distribution.
method Online-within-online setup, inner and outer learners, leveraging non-uniform empirical distribution of best arms.
result Improves regret bounds for non-uniform best arm distributions.
Online algorithm for probabilistic forecasting of conditional moments.
problem Probabilistic forecasting needs accurate learning of expected value and conditional heteroskedasticity.
method Combines online LASSO estimation with GAMLSS framework.
result Competitive performance in day-ahead electricity price forecasting.
New insights show coverage conditions are crucial for efficient online reinforcement learning.
problem The role of coverage conditions in determining sample complexity of offline reinforcement learning.
method Established a connection between coverage conditions and sample efficiency in online reinforcement learning.
result Coverability, a structural property of MDPs, enables sample-efficient exploration in online reinforcement learning.
A probabilistic framework for online test-time adaptation
problem Adapting models to new data under distributional shift
method State-space modelling architecture
result Characterizing parameter learning, time evolution, prior tuning, and prediction
OSAMD adapts online to changing distributions with limited labels.
problem Models struggle with continual distribution shifts and expensive labeling in changing environments.
method Online Active Continual Adaptation with OSAMD, an online teacher-student structure and margin-based criterion.
result OSAMD achieves favorable dynamic regret bounds under changing environments with limited labels.
New method uses offline data to improve online bandit learning, even when distributions differ.
problem Improving online bandit learning with different offline and online distributions.
method MIN-UCB policy that adapts to offline data when informative, achieving tight regret bounds.
result MIN-UCB policy outperforms UCB policy with offline data and provides tight regret bounds.
This research improves online learning by correcting for target shift in machine learning.
problem Online learning struggles with distributional shift, especially in target values.
method Derives closed-form expressions for online and offline learning, and target correction.
result Online kernel-based learning can learn the same predictor as offline learning with target correction.
Distributed, online data mining systems have emerged as a result of applications requiring analysis of large amounts of correlated and high-dimensional data produced by multiple distributed data sources. We propose a distributed online data classification framework where data is gathered by distributed data sources and…
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 algorithm reduces online learning error for unknown feature distributions.
problem Oracle-efficient hybrid online learning with unknown feature and label distributions.
method Computational efficient online predictor using ERM oracle for finite-VC and fat-shattering classes.
result Oracle-efficient sublinear regret bounds for hybrid online learning with unknown feature generation.
We study data poisoning attacks in the online setting where training items arrive sequentially, and the attacker may perturb the current item to manipulate online learning. Importantly, the attacker has no knowledge of future training items nor the data generating distribution. We formulate online data poisoning attack…
Gradient equilibrium improves online learning performance without requiring sublinear regret.
problem Achieving sublinear regret in online learning.
method Gradient equilibrium: average of gradients converges to zero.
result Gradient equilibrium can be achieved by standard online learning methods.
The area of online machine learning in big data streams covers algorithms that are (1) distributed and (2) work from data streams with only a limited possibility to store past data. The first requirement mostly concerns software architectures and efficient algorithms. The second one also imposes nontrivial theoretical …
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.
COP improves online conformal prediction by incorporating data patterns, leading to tighter prediction sets.
problem Overly conservative prediction sets in online conformal prediction methods when data distribution shifts.
method Conformal Optimistic Prediction (COP) incorporating estimated cumulative distribution function of non-conformity scores.
result COP produces tighter prediction sets with valid coverage guarantees, outperforming other methods.
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…
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.
We propose an efficient distributed online learning protocol for low-latency real-time services. It extends a previously presented protocol to kernelized online learners that represent their models by a support vector expansion. While such learners often achieve higher predictive performance than their linear counterpa…
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 method handles unknown task boundaries in continual learning.
problem Catastrophic forgetting in neural networks.
method Fixed-point equations for online variational Bayes optimization.
result Approximates online Bayes update for non-stationary data.
Paper proposes a recursive GPSSM for efficient online learning.
problem Efficient online learning for dynamical models with limited prior information.
method Recursive Gaussian Process State-Space Model with adaptive capabilities for domains and hyperparameters.
result Superior accuracy, computational efficiency, and adaptability compared to state-of-the-art methods.
The Gaussian mixture model is a classic technique for clustering and data modeling that is used in numerous applications. With the rise of big data, there is a need for parameter estimation techniques that can handle streaming data and distribute the computation over several processors. While online variants of the Exp…
CAdam optimizes online learning by adapting to distribution shifts and noise.
problem Challenges in online learning data, including distribution shifts and noise, affect Adam's performance.
method CAdam uses a confidence-based approach to assess the consistency between momentum and gradients before updating parameters.
result CAdam outperforms other optimizers in various settings with distribution shift or noise.
DOMKL learns functions from IoT data with minimal regret and consensus constraints.
problem Learning from streaming IoT data while preserving privacy.
method DOMKL combines OADMM and distributed Hedge for online learning with multiple kernels.
result DOMKL achieves optimal sublinear regret and consensus constraints.
New online conformal prediction methods minimize strongly adaptive regret and achieve near-optimal coverage.
problem Uncertainty quantification in online settings with changing data distributions.
method Developed new online conformal prediction methods that minimize strongly adaptive regret.
result Achieve near-optimal strongly adaptive regret and approximately valid coverage.
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.
A distributed algorithm for online multi-task learning reduces communication and runtime costs.
problem Heavy communication and high runtime complexity in online multi-task learning.
method Adaptive primal-dual algorithm that synchronizes data across geographically distributed tasks.
result The proposed algorithm achieves optimal regret and is effective on real-world datasets.
A new approach for test-time adaptation detects and reacts to distribution shifts.
problem Improving test-time accuracy under distribution shifts.
method Online self-training with a detection tool based on entropy values and betting martingales.
result The classifier's entropy values match those of the source domain, building invariance to distribution shifts.
Optimizes sampling from target distributions with applications to online learning.
problem Optimizing the total variation distance between target and sampled distributions.
method Analyzes the sample complexity of approximate rejection sampling and its applications.
result The optimal total variation distance is given by $ ildeΘ( rac{D}{f'(n)})$.
New algorithm for online learning in episodic MDPs with convex objectives.
problem Online episodic convex reinforcement learning.
method Online mirror descent algorithm with varying constraint sets and exploration bonus.
result Near-optimal regret bounds for online CURL without prior knowledge of transition function.
This paper tackles online reinforcement learning for unseen tasks with unknown boundaries.
problem Real-world tasks violate assumptions of task distributions, independence, and clear task delineations.
method A mixture of Gaussian Processes models different dynamics, and a transition prior handles temporal dependencies.
result The approach reliably handles task distribution shifts and outperforms alternatives in non-stationary tasks.
Online method for state estimation and parameter learning in SSMs.
problem State estimation and parameter learning in state-space models.
method Stochastic gradient optimization of variational lower bound, using backward decompositions and Bellman recursions.
result Ability to operate online without revisiting historic observations.
Optimal learning rate schedules for SGD in changing data distributions.
problem Minimizing regret in online learning with changing data distributions.
method Characterized optimal schedules for linear regression, proposed schedules for general convex and non-convex losses, and defined a notion of regret for non-convex losses.
result Upper and lower bounds for regret with constants for convex losses, and an upper bound on total expected regret for non-convex losses.
Paper tackles robust online learning with worst-case distributions.
problem Distributionally robust online learning with worst-case Wasserstein ambiguity sets.
method Formulated as an online saddle-point stochastic game, proposed a general framework converging to robust Nash equilibrium.
result Proposed a tailored algorithm for piecewise concave loss functions, achieving substantial speedups.
New learnability criteria for non-iid processes equivalent to online learning.
problem Statistical learning under non-iid stochastic processes is underdeveloped.
method Defined two learnability notions and showed their equivalence to online learning.
result Learnability criteria for non-iid processes are equivalent to online learning.
Online learning improves traffic congestion prediction over time.
problem Model degradation due to concept drift in traffic data.
method Incremental learning from non-stationary time series data.
result Performance of models degrades with increased prediction horizon.
COAD maximizes online auction revenue by quantifying uncertainty without known distributions.
problem Designing incentive-compatible mechanisms for online auctions with unknown bidder values and uncertain future participants.
method COAD uses distribution-free uncertainty quantification techniques and integrates machine learning methods to predict bidder values while ensuring revenue guarantees.
result COAD maximizes revenue in online auctions through bidder-specific reserve prices based on lower confidence bounds of valuations.
POLA adapts learning rates for online time series prediction.
problem Adapting to changing data distributions in dynamic environments.
method Adaptive learning rate regulation for recurrent neural networks.
result POLA outperforms other online prediction methods in real-world datasets.
New framework for understanding adversarial and stochastic learning.
problem Understanding the continuum from adversarial to stochastic settings in online learning.
method Distributionally constrained adversaries framework.
result Characterization of learnable distribution classes for various function classes.