New algorithm for sequential off-policy learning improves performance over batch methods.
problem Training policies from logged interaction data in a sequential setting.
method Combines Logarithmic Smoothing with online PAC-Bayesian tools.
result Improves performance and accelerates convergence in sequential off-policy learning.
Paper proposes AdaBoost-assisted ELM for efficient online sequential classification.
problem Efficient online sequential classification with improved accuracy and stability.
method Utilizes AdaBoost for cost-sensitive learning and forgetting mechanism for stability.
result Achieves 94.41% accuracy on MNIST dataset with reduced standard deviation.
Algorithm learns principal curves from data streams in a sequential manner.
problem Summarizing large data streams using PCA is challenging due to theoretical and algorithmic issues.
method Proposes a novel sequential algorithm for learning principal curves from data streams.
result Supports regret bounds with optimal sublinear remainder terms.
Study evaluates reinforcement learning algorithms for sequential experimental design.
problem Lack of generalization in reinforcement learning for experimental design.
method Investigated several reinforcement learning algorithms for sequential experimental design.
result Certain algorithms, using dropout or ensemble approaches, show attractive generalization properties.
Study on optimal rates for sequential probability assignment using smoothed analysis.
problem Optimal rates for sequential probability assignment under smoothed adversaries.
method General-purpose reduction from minimax rates to transductive learning, development of an efficient algorithm using MLE oracle.
result Optimal (logarithmic) fast rates for parametric and finite VC dimension classes, sublinear regret for general classes.
Randomized SINDy learns dynamic data structures using probabilistic methods.
problem Learning time-dependent data structures in dynamic systems.
method Sequential machine learning with a probabilistic approach, incorporating feature augmentation and Tikhonov regularization.
result Demonstrated effectiveness in regression and binary classification using real-world data.
We consider the problem of sequential prediction and provide tools to study the minimax value of the associated game. Classical statistical learning theory provides several useful complexity measures to study learning with i.i.d. data. Our proposed sequential complexities can be seen as extensions of these measures to …
Project reviews and compares imitation learning algorithms.
problem Achieving optimal performance by mimicking an expert's actions.
method Wide review and comparison of recent imitation learning algorithms.
result Comparison of algorithms' performance and regret bounds.
MACRO meta-algorithm learns from sequentially arriving data without storing all data.
problem Learning hypotheses of minimal risk for sequentially arriving dependent data.
method MACRO, a meta-algorithm that updates a set of learning subroutines iteratively.
result Improved prediction performance compared to traditional non-conditional learning.
Quantum models learn sequential data more efficiently.
problem Learning hidden quantum Markov models efficiently.
method Relaxing constraints for quantum circuit simulation, reformulating HQMMs, and developing a learning algorithm.
result Quantum models can learn sequential data with fewer states and higher accuracy.
Teaches sequential learners with changing inner states to improve future performance.
problem Teaching sequential learners with evolving inner states.
method Introduces an optimal control approach for multi-agent learning.
result Optimal control approach improves future performance of learners.
Optimal control theory improves machine teaching efficiency.
problem Finding the shortest training sequence for a sequential learning algorithm to reach a target model.
method Formulated as a time-optimal control problem, leveraging optimal control theory and computational tools.
result Optimal training sequences can vastly outperform existing heuristics.
Detects data drift in deep learning models using neural embeddings.
problem Detecting changes in data distribution in deep learning models.
method Formulates drift detection in a sequential decision framework and introduces a loss function to balance false alarms and quick detection.
result Demonstrates improved ability to balance false alarms and quick detection in change detection.
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 algorithm resists attacks, deletions, and failures in sequential system optimization.
problem Resilient sequential design in adversarial environments.
method First scalable algorithm for system-wide resiliency, adaptiveness, and provable approximation.
result Guaranteed solution close to optimal for monotone objective functions.
Extracts weighted automata from black box models for sequential data.
problem Global interpretability of black box models for symbolic sequential data.
method Spectral algorithm for extracting weighted automata from black boxes without access to inner representation.
result Approximation of black box models using inferred weighted automata is of high quality.
A lifelong learning strategy refines data representation for sequential tasks.
problem Transfer learning in an online setting with sequential tasks.
method Refines data representation for within-task algorithms, inheriting good properties.
result Inherited regret bounds for the within-task algorithm, with improved bounds for finite set of predictors.
Algorithm learns optimal arm selection in unsupervised sequential selection with contextual information.
problem Learning optimal arm selection in unsupervised sequential selection with contextual information.
method Proposes an algorithm for the contextual USS problem under the CWD property, demonstrating sub-linear regret.
result Demonstrates sub-linear regret for the proposed algorithm.
OMLE combines optimism and MLE for efficient sequential decision making.
problem Efficiently solving sequential decision making problems, especially in partially observable settings.
method Combines optimism for exploration and maximum likelihood estimation for model learning.
result OMLE learns near-optimal policies for a wide range of sequential decision making problems.
Deep learning automates decoding of sequential codes.
problem Automating the discovery of decoding algorithms in coding theory.
method Study of recurrent neural network (RNN) architectures for decoding well-known sequential codes.
result RNN architectures can decode well-known sequential codes with close to optimal performance.
Algorithm learns to play against unknown opponents in sequential games.
problem Designing strategies for a learner to interact with an unknown opponent in repeated sequential games.
method Kernel-based regularity assumptions and a novel algorithm combining bilevel optimization and online learning.
result Algorithm achieves sublinear regret guarantees and is effective in specific game settings.
COT-GAN generates sequential data with a causal optimal transport approach.
problem Generating sequential data with temporal causality constraints.
method Adversarial training with Causal Optimal Transport (COT) and entropic penalization.
result COT-GAN effectively learns time-dependent data distributions and generates stable time series data.
Adaptive algorithm learns latent dynamical systems from sequential data.
problem Learning low-dimensional latent dynamical systems from high-dimensional sequential data.
method Combines amortized inference with path integral control to approximate inference.
result Proposed method leads to tighter lower bounds in sequential data learning.
Develops a new framework for analyzing sequential decision-making problems using information theory.
problem Lack of information-theoretic generalization bounds for sequential decision-making problems.
method Introduces a sequential supersample framework that separates learner filtration from proof-side enlargement, controlling the generalization gap by sequential CMI.
result Establishes a sequential CMI that controls the generalization gap in sequential decision-making problems.
Two bandit frameworks for learning the distribution with highest mean.
problem Learning which distribution has the highest mean among a set of distributions.
method Asymptotically optimal algorithms for regret minimization and best arm identification.
result Comparison of sampling rules and complexity terms for both problems.
New algorithm adapts to changing action sets in sequential decision making.
problem Adapting to a changing action set in sequential decision making problems.
method Breaks the problem into inferring action structure and optimizing policy.
result Demonstrates efficiency on real-world lifelong learning problems.
Algorithm identifies Pareto front in multi-objective bandits efficiently.
problem Sequentially learning the Pareto front in multi-objective bandits.
method Efficient algorithm achieving optimal sample complexity.
result Correct answer with high probability in minimal rounds.
Study batch learning in linear bandits with context, achieving near-optimal performance.
problem Sequential batch learning in linear contextual bandits with finite actions.
method Established regret bounds and provided algorithms for two settings: arbitrary contexts and i.i.d. contexts.
result Regret upper bound nearly matches lower bound, showing polynomial and logarithmic batch requirements.
New tighter confidence bounds for sequential kernel regression.
problem Quantifying uncertainty in sequential learning algorithms.
method Martingale tail inequalities and conic programming.
result New confidence bounds are tighter than existing ones.
Proposed SMO algorithm for OC-SVM+ significantly outperforms non-sequential algorithms.
problem One-class SVM with privileged information
method Sequential Minimal Optimization (SMO) algorithm
result Finite-time convergence established
New algorithm combines curriculum learning with HER for complex object manipulation tasks.
problem Learning complex sequential object manipulation tasks from scratch is challenging.
method Curriculum learning with Hindsight Experience Replay (HER) for recurrent object manipulation tasks.
result Significant improvement in learning sequential object manipulation tasks compared to vanilla-HER.
Algorithm learns transition matrices of multiple unknown Markov chains.
problem Learning transition matrices of multiple unknown Markov chains.
method Adaptive allocation of Markov chains for sequential learning.
result Algorithm efficiently balances exploration and exploitation, achieving optimal asymptotic loss.
Machine teaches IRL with minimal demonstrations.
problem Finding the minimum set of demonstrations for IRL.
method Formalized as a machine teaching problem, reduced to set cover, approximated efficiently.
result Efficient algorithm for determining maximally informative demonstrations.
New reinforcement learning bound improves generalization for sequential data.
problem Challenges in obtaining generalization guarantees for reinforcement learning due to sequential data.
method PAC-Bayesian reinforcement learning with consideration of Markov dependencies and mixing time.
result Demonstrated practical utility through PB-SAC, providing meaningful confidence certificates.
New algorithms ensure fairness in sequential decisions, accounting for feedback effects.
problem Ignoring feedback effects can lead to unfair outcomes in sequential decision-making.
method Model feedback effects as MDPs and propose fair properties and algorithms.
result Demonstrated the necessity of considering dynamical effects for fairness.
New algorithms identify optimal moves in game trees.
problem Identifying the best move in a game tree quickly.
method Best arm identification procedure applied to depth-one summaries.
result New algorithms outperform existing methods.
Interpretable RNN uses sparse recovery for better performance.
problem Interpreting the internal workings of RNNs.
method Sequential Sparse Recovery + SISTA algorithm.
result SISTA-RNN achieves better performance and is more interpretable.
A new method reduces hyperparameter tuning evaluations by using sequential tests.
problem Time-consuming hyperparameter tuning in machine learning.
method Sequential Random Search (SQRS) extending regular random search.
result SQRS finds similarly well-performing parameter settings with fewer evaluations.
New private algorithm for sequential hypothesis testing with privacy and error rate guarantees.
problem Privacy protection in sequential hypothesis testing for sensitive data.
method Renyi differential privacy, Wald's Sequential Probability Ratio Test (SPRT).
result Private algorithm with strong privacy guarantees and theoretical performance analysis.
A sequential learning framework improves domain generalization performance.
problem Training models robust to domain shift across multiple domains.
method Inspired by lifelong learning, a sequential training approach optimizing for all following domains.
result Improves performance on DG benchmarks with a simple, fast algorithm.
SNPLA uses normalizing flows for efficient inference in implicit models.
problem Efficient inference in implicit models with complex likelihood and posterior learning.
method Sequential Neural Posterior and Likelihood Approximation (SNPLA) algorithm using normalizing flows.
result SNPLA achieves competitive performance with faster posterior draws compared to MCMC methods.
SYMSGD improves parallel SGD by combining local models to match sequential SGD's results.
problem Inherently sequential nature of SGD limits parallel scalability and convergence.
method SYMSGD combines local models with a combiner to mimic sequential SGD's semantics.
result SYMSGD achieves up to 11x speedup on 16 cores compared to a sequential baseline.
This review assesses deep-learning methods for complex sequential data.
problem Lack of robustness and transparency in deep-learning frameworks for irregular sequential data.
method Systematic literature review of existing algorithms.
result Recurrent neural networks dominate in performance evaluation of deep-learning frameworks.
New algorithms for fast online decision making using neural networks and martingale posteriors.
problem Online sequential decision making under uncertainty.
method Martingale posterior neural networks for fast online learning and decision making.
result Achieves competitive performance-speed trade-offs in non-stationary contextual bandits and Bayesian optimization.
This thesis analyzes MACL systems with low-regret learning algorithms for sequential decision making.
problem Designing efficient learning algorithms for multi-agent cooperative systems to minimize regret.
method Analyzes and develops algorithms for cooperative multi-agent multi-armed bandit problems and online convex optimization in distributed settings.
result Presented regret lower bounds and efficient algorithms for achieving these bounds, providing guidance on communication protocols.
Survey of algorithms to correct past mistakes in prediction.
problem Improving prediction accuracy by correcting past errors.
method Defensive Forecasting as a sequential game theory approach to minimize prediction metrics.
result Simple, near-optimal algorithms for various prediction tasks.
New algorithms handle unpredictable actions in sequential learning.
problem Learning with unreliable composite actions in online optimization.
method Follow-The-Perturbed-Leader method with Counting Asleep Times loss estimation.
result Significant improvement in performance guarantees for sleeping bandit problem.
Co-training improves sequential decision-making policies from multiple views.
problem Learning policies in settings with multiple state-action representations.
method Inspired by co-training for classification, we present a co-training framework for sequential decision making.
result Our framework improves upon learning from a single view alone.