Transforms offline algorithms to online with low regret in random order model.
problem Developing online algorithms with low approximate regret from offline approximation algorithms.
method General reduction theorem and coreset construction method.
result Achieves polylogarithmic ε-approximate regret for various online problems.
Paper proposes an online speech recognition model using Transformer.
problem Challenges in deploying Transformer-based E2E ASR for online speech recognition.
method Chunk self-attention encoder (chunk-SAE) and monotonic truncated attention (MTA) based self-attention decoder (SAD).
result Achieved 23.66% CER with 320 ms latency, significant improvement over offline models.
A novel online GP model captures long-term memory in sequential data.
problem Capturing long-term memory in sequential data online.
method Integrates HiPPO framework into interdomain GP, leveraging time-varying orthogonal projections as inducing variables.
result OHSVGP outperforms existing online GP methods in predictive performance, long-term memory preservation, and computational efficiency.
Predicts student performance in interactive online question pools using GNNs.
problem Predicting student performance in interactive online question pools with evolving knowledge.
method Proposes R^2GCN, a GNN model for heterogeneous networks to predict student performance.
result Achieves higher accuracy in student performance prediction than traditional methods.
SpectralLeader learns latent variables from streaming data efficiently and globally.
problem Learning latent variable models from a stream of data efficiently and globally.
method SpectralLeader, an online learning algorithm for latent variable models that converges to the global optimum.
result SpectralLeader achieves a sublinear upper bound on n n n -step regret in the bag-of-words model. New definition of regret for nonconvex online learning models.
problem Intractability of standard regret measures for nonconvex models.
method Introduced a local gradient based regret definition.
result Our definition provides more interpretable bounds for forecasting.
Efficiently handles large support vectors in kernelized online learning.
problem Efficiency in communication for large support vectors in kernelized models.
method Extends a previously proposed protocol to kernelized online learners, introducing a novel communication criterion.
result Communication is bounded by the loss suffered, improving efficiency.
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.
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.
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.
Efficient model selection framework for online learning without parameter tuning.
problem Model selection in online learning without predefined parameters.
method Generic meta-algorithm framework for model selection in arbitrary Banach spaces under mild smoothness assumptions.
result First computationally efficient parameter-free algorithms in arbitrary Banach spaces.
Study of online learning with noisy feedback in adversarial settings.
problem Adversarial online learning with noisy feedback.
method Models of adversarial online learning with binary losses xored by noise, considering both constant and variable noise rates.
result Tight regret bounds for learning with noise in adversarial online learning.
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.
Extends quantum learning theory to multiclass and online settings.
problem Quantum learning theory for batch and online learning.
method Adapts classical models to quantum settings, introduces new online learning model.
result Quantum and classical sample complexities have the same form for various learning scenarios.
Paper tackles continual reinforcement learning by forgetting, proposing a planning method with online world models.
problem Catastrophic forgetting in reinforcement learning when learning new tasks.
method Planning with an online world model using model predictive control.
result The proposed FTL Online Agent (OA) learns new tasks without forgetting old skills.
Paper addresses online alignment of large language models under uncertain preference feedback.
problem Online alignment of large language models with misspecified preference feedback.
method Formulates an oracle-robust objective as a worst-case optimization problem for log-linear policies, and develops projected stochastic composite updates.
result Shows that the robust objective admits an exact closed-form decomposition and achieves O ~ ( ε − 2 ) \widetilde{O}(\varepsilon^{-2}) O ( ε − 2 ) oracle complexity. 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.
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.
Paper develops online learning algorithms for quaternion ARMA models.
problem Adaptive learning for autoregressive moving average (ARMA) models in quaternion domain.
method Transformed learning problem into full information optimization task, solved using gradient descent and Newton's method.
result Online algorithms achieve asymptotic performance approaching best ARMA model.
Revisits online Laplace methods for neural networks, showing they are sound under certain conditions.
problem Online Laplace methods violate the Laplace approximation's critical assumption.
method Re-derives online Laplace methods, showing they target a variational bound on a mode-corrected variant of the Laplace evidence.
result Online Laplace and its mode-corrected counterpart share stationary points that satisfy the Laplace method's assumption.
Paper proposes a new dynamic pricing method with always-valid online statistical learning.
problem Designing dynamic pricing policies that adapt to online uncertainty and maintain validity.
method Regularized online statistical learning with theoretical guarantees and three major advantages.
result Proposed OORMLP pricing policy secures logarithmic regret in decision horizon.
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.
Paper develops a method for rapid online learning of deep models.
problem Rapid adaptation of deep models to changing tasks.
method Uses meta-learning to train a model that can adapt to new tasks and recall old ones.
result Meta-learning enables effective continuous adaptation in non-stationary task distributions.
R package for online forecasting in various fields.
problem Frequent updates of forecasts in online settings.
method Generalized setup for time-adaptive fitting of dynamical and non-linear models.
result Effective use of forecasts as model inputs in operational settings.
Study examines complexity of opinions in online discussions.
problem Understanding the complexity and similarity of opinions in online discussions.
method Developed a modeling framework to construct latent representations of opinions, connecting them to voting models and sign-rank of a matrix.
result Found that unidimensional models often fail to accurately represent online discussions, revealing insights into human judgements and opinions.
SAIL improves online alignment of large language models with minimal feedback.
problem Offline RLHF methods often lead to sub-optimal performance due to fixed preference datasets.
method SAIL uses bilevel optimization and a single-level first-order method to iteratively refine model alignment.
result SAIL significantly improves alignment performance on open-sourced datasets with minimal computational overhead.
PQR model tackles online learning with high-dimensional data.
problem Online learning with high-dimensional data and non-convex quadratic regression.
method Projective Quadratic Regression (PQR) model capturing second-order feature information, convexity, and applicability of existing optimization methods.
result PQR model achieves global optimal solution and handles high-dimensional data efficiently.
New online feature selection method handles streaming data with concept drift.
problem Handling streaming data with concept drift and sparsity.
method Online feature screening method with model adaptation.
result Online screening methods with model adaptation outperform without model adaptation on data streams with concept drift.
We provide an online RLHF workflow for large language models.
problem Lack of online RLHF workflow for large language models.
method Construct preference models using open-source datasets, approximate human feedback, and implement online iterative RLHF.
result Our LLM achieves state-of-the-art performance on various benchmarks.
ELF improves FM forecasts by efficiently using online feedback.
problem Fixed FMs fail to adapt to current data characteristics.
method ELF-Forecaster learns current data distribution, ELF-Weighter combines forecasts.
result ELF improves FM forecasts across various datasets.
Study online learning with set-valued feedback, showing differences between deterministic and randomized approaches.
problem Online learning with set-valued feedback, where labels are sets rather than single labels.
method Introduced new combinatorial dimensions (Set Littlestone and Measure Shattering) to characterize learnability.
result Characterized deterministic and randomized online learnability, and established bounds for various learning settings.
Study improves online learning with adaptable agents in various settings.
problem Learning with improving agents in online settings.
method Extensive analysis of combinatorial dimensions, multiclass setup, bandit feedback, and agent cost.
result Characterization and analysis of online learnability in the model.
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.
A new method for online VI in SSMs using asymptotic contrast.
problem Lack of functionality for streaming data in standard VI methods for SSMs.
method Propose maximising an IWAE-type variational lower bound on the asymptotic contrast function using stochastic approximation.
result OSIWAE allows for online learning of model parameters and latent states.
Develops a framework to control risk in online learning models.
problem Rigorous uncertainty quantification for online learning models.
method A framework for constructing uncertainty sets that provably control risk.
result Guarantees risk control at any user-specified level even with distribution shifts.
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.
Online machine learns from signals robustly using consensus optimization.
problem Signal classification in online settings.
method Reproducing kernel Hilbert space with consensus optimization.
result Robust signal classification achieved.
Unified framework for online learning in click prediction for search ads.
problem Model staleness leading to accuracy and calibration degradation over time.
method Two paradigms of Batch Online Learning: early stopping and proximal regularization.
result Two OL schemes are closely related and can be traded-off between new and historical data.
Bayesian method improves online NARMAX model identification.
problem Online identification of nonlinear systems with small sample sizes and low noise.
method Variational Bayesian inference using message passing algorithm for polynomial NARMAX models.
result Variational Bayesian estimator outperforms recursive and offline least-squares methods.
Unified EM interpretation for online parameter estimation.
problem Parameter estimation of hidden variable models.
method Model-level interpretation of EM as relative entropy divergences, leading to online updates.
result Unified online EM algorithm for various models.
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.
Simplifies online learning with consistent oracle to fewer mistakes.
problem Online learning with computationally intractable Littlestone dimension computation.
method Novel algorithm making at most O ( 256 d ) O(256^d) O ( 25 6 d ) mistakes, simpler proof. result No algorithm can make less than 3 d 3^d 3 d mistakes. Paper addresses inconsistency between offline and online LTR performance.
problem Inconsistency between offline and online LTR performance in E-commerce.
method Proposes an evaluator-generator framework to maximize evaluator score using reinforcement learning.
result Significant improvement in Conversion Rate (CR) over existing models.
A new online learning algorithm for graph-structured sparsity.
problem Efficiently handling graph-structured sparsity constraints in online learning settings.
method Proposes extsc{GraphDA} algorithm that projects gradients and variables onto subspaces.
result Improves classification performance and captures graph-structured features effectively.
New RL algorithm tackles online robust MDPs with uncertainty.
problem Developing robust reinforcement learning models for real-world environments.
method Proposes a robust optimistic policy optimization algorithm for online robust MDPs.
result Establishes the first regret bound for online robust MDPs.
This article surveys online machine learning in big data streams.
problem Limited storage for past data in data streams.
method Distributed software architectures and libraries for efficient algorithms.
result Overview of classification, regression, recommendation, and unsupervised models for streaming data.
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.
New online few-shot learning model for context-aware recognition.
problem Few-shot learning in online, continuous settings with spatiotemporal context.
method Proposed new dataset and online versions of existing few-shot learning approaches.
result Contextual prototypical memory model improves performance.