Algorithm learns from offline data to improve performance in target environment.
problem Learning from offline data in a target environment with unknown shifts.
method Adaptive algorithm that uses offline data to improve performance when informative.
result Algorithm provably improves performance over purely online learning when offline data are informative.
Optimizes particle filtering for non-stationary environments.
problem Tracking and adapting to non-stationary environments in online prediction.
method Formulated an efficient particle filtering method using online mirror descent algorithm.
result Achieves optimal particle efficiency in non-stationary environments.
Adapts to new environments in robotics using latent variable models.
problem Learning dynamics in robotic environments with subtle variations.
method Variational inference for latent representation, online Bayesian inference, neural network ensemble.
result Positive transfer during training and online adaptation on HalfCheetah task.
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.
Adaptive PCA algorithms for changing environments.
problem Static adversarial regret is not suitable for changing environments.
method Online adaptive algorithms for PCA and variance minimization with sub-linear adaptive regret guarantees.
result The proposed algorithms adapt to changing environments.
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.
The Open University studies student online behavior in virtual learning environments.
problem Improving retention rates in online modules.
method GUHA and Markov chain-based analysis of student activity.
result Both methods are valid for modeling student activities.
New model-based methods adapt pre-trained policies to unseen environments efficiently.
problem High sample complexity in reinforcement learning limits practical applications.
method Combines online learning and adaptive control to adapt policies in unseen environments.
result Proves policies can quickly recover trajectories from source to target environments.
Robots learn quickly from few interactions using mental replay and intrinsic motivation.
problem Continuous online adaptation for robots in changing environments.
method Bio-inspired stochastic recurrent neural network with learning signals and mental replay.
result Robots can adapt to novel environments in seconds from few interactions.
Paper develops adaptive learning method to minimize dynamic regret in dynamic environments.
problem Bounding dynamic regret in online convex optimization for dynamic environments.
method Adaptive Learning for Dynamic Environment (Ader) method, combining multiple experts and an expert-tracking algorithm.
result Achieves optimal O ( T ( 1 + P T ) ) O(\sqrt{T(1+P_T)}) O ( T ( 1 + P T ) ) dynamic regret, closing the gap from previous O ( T ( 1 + P T ) ) O(\sqrt{T(1+P_T)}) O ( T ( 1 + P T ) ) lower bound. Adaptive online learning algorithm improves history forgetting in nonstationary environments.
problem Adversarial nonstationary environments where future data can be very different from past data.
method Discounted regret in online convex optimization, FTRL-based algorithm, adaptive learning rate.
result Improves classical gradient descent with constant learning rate in online convex optimization.
This thesis improves OCO algorithms for dynamic data environments.
problem Sequential, changing data in big data environments.
method Designing algorithms to adapt to changing environments.
result Improved algorithms for online resource allocation.
Proximal online gradient minimizes dynamic regret in evolving environments.
problem Optimizing dynamic regret in online learning where the optimal solution changes over time.
method Proximal online gradient method, showing it is optimal for dynamic regret.
result Proximal online gradient matches the lower bound for dynamic regret, proving its optimality.
This work tackles online adaptation for reinforcement learning in dynamic real-world environments.
problem Expensive sample generation and failure of specialized policies in the real world.
method Meta-learning to train a dynamics model prior that can be rapidly adapted to new contexts.
result Demonstrated online adaptation for continuous control tasks in both simulated and real-world agents.
The rise in online social networking has brought about a revolution in social relations. However, its effects on offline interactions and its implications for collective well-being are still not clear and are under-investigated. We study the ecology of online and offline interaction in an evolutionary game framework wh…
New meta algorithm improves adaptability in changing environments.
problem Adapting to changing environments in online learning.
method Derives a new parameter-free algorithm for the LEA problem, inspired by coin betting.
result Strongly-adaptive regret bound is log ( T ) \sqrt{\log(T)} log ( T ) better than other algorithms. HySRL improves RL sample efficiency with shifted-dynamics data.
problem Leveraging historical data with shifted dynamics to improve sample efficiency in RL.
method HySRL, a hybrid transfer RL algorithm that uses prior information on dynamics shift to achieve better sample complexity.
result HySRL achieves problem-dependent sample complexity and outperforms pure online RL.
Paper tackles online label shift in real-world applications.
problem Adapting to changing label distributions in online learning.
method Formulated an unbiased risk estimator and proposed online ensemble algorithms.
result Achieved optimal dynamic regret, indicating adaptability to label shift.
New algorithms reduce dynamic regret for convex and smooth functions in non-stationary environments.
problem Online convex optimization in non-stationary environments.
method Proposed novel online algorithms exploiting smoothness to reduce dynamic regret.
result Dynamic regret improved to O ( T ) \mathcal{O}(T) O ( T ) for convex and smooth functions. We introduce a new local regret framework for non-convex models in dynamic environments.
problem Challenges in online forecasting for non-convex models with frequent updates and concept drift.
method We propose a novel local regret framework and a time-smoothed gradient update rule.
result Our approach yields more stable, robust, and computationally efficient forecasting compared to state-of-the-art methods.
Fine-tuning RL with offline data reduces online interactions.
problem Optimizing RL with limited online interactions and offline data.
method Developed algorithm extsc{FTPedel} for MDPs with linear structure.
result Optimally reduces the number of online interactions needed.
Two adaptive algorithms improve tracking regret in dynamic expert advice problems.
problem Prediction with expert advice in dynamic environments.
method Developed two adaptive and efficient algorithms using online mirror descent framework.
result Achieved data-dependent tracking regret bounds for both algorithms.
Method learns attractive areas from agent motions to represent environments.
problem Representing environments based on moving agents' nonlinear motions.
method Switching model of velocity fields, parametric representation of attractive spots.
result Dynamic map of attractive areas for online learning.
New algorithms adapt to friendly environments in online learning.
problem Oracle-efficient algorithms struggle with friendly environments.
method Follow-the-perturbed-leader algorithms with approximability condition.
result Best-of-both-worlds bound in oracle-efficient setting.
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.
LF-IBIS learns optimal policies online without explicit likelihood.
problem Bayesian RL challenges due to intractable likelihood functions.
method Combines ABC with IBIS for online belief updates.
result Approximates posterior distributions for policies and parameters.
Episodic memory helps online model selection in complex environments.
problem Online model selection in complex, real-world environments.
method Episodic memory to retain data points and compute necessary quantities for model selection.
result Episodic memory can resolve the challenge of online model selection with limited memory.
New algorithms minimize regret in changing environments for piecewise Lipschitz functions.
problem Optimizing in unpredictable, time-varying conditions for piecewise Lipschitz functions.
method Introduced shifting regret as a metric, and provided bounds for O ( s d T log T + s T 1 − β ) O(\sqrt{sdT\log T}+sT^{1-β}) O ( s d T log T + s T 1 − β ) . result Improved bounds for β β β -dispersed functions, with empirical validation in online clustering. Optimal algorithms for mixable losses in dynamic environments with reduced redundancy.
problem Online optimization of mixable loss functions in a dynamic environment.
method Introduce online mixture schemes with polynomial and logarithmic time complexities.
result Achieves optimal redundancy up to a constant multiplicity gap.
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.
Improved online gradient descent with fewer queries for dynamic environments.
problem Efficiently tracking changes in functions with varying gradients and smoothness.
method Developed a new theoretical framework to analyze online gradient descent in dynamic settings, reducing query complexity.
result Achieved state-of-the-art dynamic regret with significantly fewer gradient queries, independent of condition number.
POPLIN improves model-based planning in complex environments.
problem Efficient planning in complex high-dimensional environments.
method Combines policy networks with online planning, optimizing parameters directly.
result POPLIN achieves state-of-the-art performance in MuJoCo benchmarks, 3x more sample efficient.
BAM integrates new data while selectively remembering past observations.
problem Slow adaptation and convergence to incorrect parameter values in non-stationary environments.
method Bayes' theorem with adaptive memory selection.
result BAM generalizes and demonstrates continuous adaptation in changing environments.
Study online ranking in non-stationary environments with abrupt preference changes.
problem Online learning to rank in a non-stationary cascade model where user preferences change abruptly.
method Cascading non-stationary bandits, proposing CascadeDUCB and CascadeSWUCB algorithms.
result Upper and lower bounds on regret for cascading non-stationary bandits algorithms.
New insights link no-regret learning to online conformal prediction in adversarial settings.
problem Understanding the relationship between no-regret learning and online conformal prediction in adversarial environments.
method Analysis of existing algorithms and new connections between no-regret learning and conformal prediction.
result No-regret learning algorithms can provide group-conditional coverage guarantees in adversarial settings.
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.
Universal algorithm minimizes adaptive regret for various convex functions.
problem Minimizing adaptive regret in changing environments for multiple convex functions.
method Borrowing MetaGrad's idea of multiple learning rates and using sleeping experts.
result First universal algorithm for minimizing adaptive regret of convex functions.
Paper tackles online convex optimization with stochastic constraints.
problem Online convex optimization with stochastic constraints.
method Proposes a new algorithm achieving O ( T ) O(\sqrt{T}) O ( T ) expected regret and constraint violations and O ( T log ( T ) ) O(\sqrt{T}\log(T)) O ( T log ( T )) high probability regret and constraint violations. result Achieves optimal regret and constraint violation bounds.
Study online RL with mismatched dynamics, achieving sublinear regret.
problem Exploration challenges in online RL with mismatched training and deployment dynamics.
method Introduce supremal visitation ratio, propose efficient algorithm with f f f -divergence. result Achieves sublinear regret in online RMDPs with optimal dependence on supremal visitation ratio and interaction episodes.
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.
Optimal online linear regression in dynamic environments using discounted Vovk-Azoury-Warmuth forecaster.
problem Achieving optimal performance in dynamic online linear regression without prior knowledge.
method Developed a discounted variant of the Vovk-Azoury-Warmuth forecaster to achieve optimal dynamic regret guarantees.
result Achieved dynamic regret of the form $O\left(d\log(T)\vee \sqrt{dP_{T}^γ(\vec{u})T}
ight)$ , with a learnable discount factor.
High-velocity streams of high-dimensional data pose significant "big data" analysis challenges across a range of applications and settings. Online learning and online convex programming play a significant role in the rapid recovery of important or anomalous information from these large datastreams. While recent advance…
A method for Bayes-Adaptive Deep RL using meta-learning.
problem Maximizing expected return in unknown environments with uncertainty.
method variBAD: meta-learning for approximate inference and task uncertainty.
result variBAD achieves higher online return than existing methods in MuJoCo domains.
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.
New algorithms adaptively calibrate predictions in non-stationary environments, matching optimal rates.
problem Designing online prediction algorithms that adapt to varying levels of non-stationarity.
method Epoch-based scheduling and non-uniform partitioning of the prediction space.
result Achieves adaptive calibration guarantees under multiple measures with optimal rates.
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. This paper tackles online strategic decision making with asymmetry and knowledge transportability.
problem Strategic decision making with information asymmetry and knowledge transportability challenges.
method Developed a sample-efficient algorithm for online learning under these conditions.
result Proved sample complexity of O ( 1 / ε 2 ) O(1/ε^2) O ( 1/ ε 2 ) for learning an ε ε ε -optimal policy. 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.