Reduces change detection to estimation using confidence sequences.
problem Detecting changes in data streams with minimal delay and false alarms.
method Reduction from sequential change detection to sequential estimation using confidence sequences.
result Change detection scheme with minimal structural assumptions and strong guarantees.
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.
This paper develops a novel deep recurrent neural network for sequential signal reconstruction.
problem Sequential signal reconstruction from low-dimensional measurements.
method Unfolding a reweighted ℓ 1 \ell_1 ℓ 1 - ℓ 1 \ell_1 ℓ 1 minimization algorithm to design a deep recurrent neural network. result The proposed reweighted-RNN significantly outperforms existing RNN models in sequential frame reconstruction.
Analyze convergence of SGD with biased updates using LMI.
problem Convergence analysis of SGD with computation errors.
method Develops sequential minimization approach to analyze trade-offs.
result Obtains convergence formulas for biased SGD.
Protocol learns pure quantum states with minimal disturbance.
problem Efficiently learn quantum states with minimal disturbance.
method Sequential measurements with minimal disturbance.
result Achieves maximal precision with polylogarithmic regret.
This work explains why GANs are less used for NLP tasks.
problem Why adversarial approaches like GANs are not widely used for NLP tasks.
method Theoretical analysis and reductions showing that maximizing likelihood is equivalent to minimizing distinguishability for certain models.
result Maximizing likelihood is as effective as minimizing distinguishability for NLP tasks.
Efficient algorithms identify true hypothesis from many options with minimal actions.
problem Identifying true hypothesis from a large set of options with minimal actions.
method Greedy approximation algorithms for active sequential hypothesis testing.
result First approximation guarantees for ASHT, independent of the number of hypotheses.
Optimal unimodal fitting for linear loss functions in a sequential, efficient manner.
problem Optimal unimodal transformation of univariate model scores under linear loss functions.
method Proposes a sequential approach to estimate the optimal rectangular fit for observed samples with each new sample.
result Sequential approach achieves optimal efficiency with logarithmic time complexity per iteration.
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
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.
PF-based FSO methods improve on SGD and IPM for large-scale empirical risk minimization.
problem Optimizing large-scale empirical risk minimization problems efficiently.
method Developed PF-based stochastic optimizers (PFSOs) based on FSO methods.
result PFSOs outperform SGD, vanilla IPM, and KF-type FSO methods in stability, speed, and flexibility.
SOR-Mamba improves Mamba for robust time series forecasting by minimizing channel order bias.
problem Robust time series forecasting with Mamba's sequential order bias.
method SOR-Mamba incorporates regularization to minimize channel order discrepancy and introduces CCM for channel correlation preservation.
result SOR-Mamba enhances robustness to channel order and improves forecasting accuracy.
SEEK algorithm selects minimal state in reinforcement learning for better policy learning.
problem Challenges in obtaining a state representation that is parsimonious and satisfies the Markov property.
method SEEK algorithm estimates the minimal sufficient state in reinforcement learning.
result The SEEK algorithm achieves selection consistency in large samples.
The ultimate goal of optimization is to find the minimizer of a target function.However, typical criteria for active optimization often ignore the uncertainty about the minimizer. We propose a novel criterion for global optimization and an associated sequential active learning strategy using Gaussian processes.Our crit…
NGP selects N features from P using neural networks in a greedy, iterative process.
problem Feature selection for non-linear prediction problems.
method Neural Greedy Pursuit (NGP) algorithm, selecting features sequentially in an iterative loss minimization procedure.
result NGP provides better performance than DeepLIFT and Drop-one-out loss methods.
Constructs classifiers for neural networks with specific data configurations.
problem Finding global minima of deep ReLU neural networks on sequentially separable data.
method Explicitly constructs zero loss neural network classifiers using cumulative parameters and truncation maps.
result Global minimizers can be described with a limited number of parameters based on the data structure.
This paper speeds up OCSSVM training using SMO.
problem Training One-Class Slab SVMs is slow.
method Uses updated SMO to divide large problems into smaller, analytically solvable subproblems.
result Training OCSSVMs scales better with large datasets.
The paper improves SVR with linear constraints for better model properties.
problem Improving Support Vector Regression with linear constraints.
method Generalized SMO algorithm for solving optimization with linear constraints.
result The proposed method shows better practical performance on various datasets.
A sequential classifier minimizes test samples for binary and multi-class classification.
problem Minimizing test samples for sequential classification with unknown distributions.
method Proposes a classifier for binary and multi-class problems, analyzing error probabilities and extending results.
result Significant advantage over non-sequential classifiers, achieving same exponents without rejection option.
The paper evaluates dynamic hedging strategies for various financial products.
problem Pricing derivative products with dynamic hedging and issuer-tailored risk.
method Unified constrained discrete stochastic dynamic programming framework with sequential local minimizing strategies.
result Demonstrates flexibility of the unified framework through numerical examples.
The paper proposes an efficient method for estimating ATEs using adaptive experiments.
problem Estimating average treatment effects (ATEs) with minimal sample size and high accuracy.
method The paper defines and uses the efficient treatment-assignment probability to sequentially assign treatments, estimating ATEs using an Adaptive Augmented Inverse Probability Weighting (A2IPW) estimator.
result The proposed experimental design and A2IPW estimator achieve the minimized semiparametric efficiency bound and provide anytime valid confidence intervals for early stopping.
New method learns disentangled signals without prior or model constraints.
problem Learning disentangled signals from data without prior or model constraints.
method Minimizes conditional KL divergence using a sequential algorithm to learn de-mixing flow models.
result Method learns self-sufficient signals that can reconstruct missing values.
Algorithm clusters items by sequentially selecting features, minimizing observations.
problem Clustering items based on bandit feedback with many features.
method Sequential Halving algorithm for feature selection.
result Accurate recovery of item partition with minimal observations.
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.
Study classifies poetry by poet using text categorization techniques.
problem Classifying poetry based on the poet who wrote it.
method Constructed a data set of English poetry, applied text categorization techniques, used Chi-Square for feature selection, and tested five classification algorithms.
result Sequential minimal optimization achieved a 70% classification success rate.
New framework improves LLM performance by avoiding forgetting during sequential training stages.
problem Forgetting during sequential training stages of LLMs.
method Proposes a joint post-training framework with theoretical convergence guarantees.
result Empirically outperforms sequential post-training framework by up to 23%.
Study optimizes zero-order strongly convex function minimization with higher order smoothness.
problem Optimizing a strongly convex function with noisy evaluations.
method Randomized approximation of projected gradient descent with smoothing kernel.
result Upper bounds and minimax lower bounds for the algorithm, showing near-optimality.
Algorithm optimizes ε-SVR with MAPE loss and sample-dependent constraints.
problem Optimizing ε-SVR with MAPE loss and sample-dependent constraints.
method Sequential Minimal Optimization (SMO) for ε-SVR with MAPE loss and sample-dependent box constraints.
result Algorithm achieves lowest median runtime on every tested configuration.
Adaptive batching improves Gaussian process surrogates for noisy level set estimation.
problem Learning the level set of noisy simulator responses.
method Developed four novel adaptive batching schemes for Gaussian process metamodels.
result Adaptive batching brings significant computational speed-ups with minimal loss of modeling fidelity.
ALMAB-DC optimizes expensive black-box experiments using active learning and distributed computing.
problem Efficiently optimizing expensive, gradient-free objectives in computational statistics and machine learning.
method Combines active learning, multi-armed bandits, and distributed asynchronous computing.
result Achieves lower simple regret and superior performance in various tasks compared to non-ALMAB baselines.
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. 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.
Adversarial dropout improves RNNs' performance on sequential data tasks.
problem Improving generalization performance of RNNs for sequential data.
method Adversarial dropout technique for RNNs using intentionally generated dropout masks.
result Adversarial dropout improves RNNs' effectiveness on sequential tasks.
Generative networks minimize predictive scoring rules for probabilistic forecasting.
problem Evaluating and improving probabilistic forecasts using generative models.
method Training generative networks to minimize predictive-sequential scoring rules on temporal sequences.
result Our method outperforms adversarial approaches in probabilistic calibration.
M-FISHER detects and adapts to streaming data shifts with statistical validity and stability.
problem Detecting and adapting to distributional shifts in streaming data.
method Constructs an exponential martingale from non-conformity scores and applies Ville's inequality for detection. Fisher-preconditioned updates for adaptation.
result Establishes M-FISHER as a principled approach for robust, anytime-valid detection and geometrically stable adaptation.
New method tunes SMC samplers efficiently without high costs.
problem Tuning SMC samplers with unadjusted kernels is challenging.
method Greedy Incremental Divergence Minimization (GIDM) for step size tuning.
result GIDM reduces KL divergence and tunes SMC samplers efficiently.
Universal preconditioning reduces sequential prediction regret.
problem Improving sequential prediction performance.
method Convolve target sequence with orthogonal polynomial coefficients.
result First sublinear and hidden-dimension-independent regret bounds.
SupSup model learns thousands of tasks without forgetting, using randomly initialized subnetworks.
problem Sequentially learning many tasks without forgetting.
method Randomly initialized base network with task-specific subnetworks (supermasks).
result Gradient-based optimization can identify the correct subnetwork for new tasks.
New method estimates policy performance under unobserved confounding.
problem Estimating policy performance when decisions depend on unobserved variables.
method Developed worst-case bounds for robust OPE under unobserved confounding.
result Efficient procedure for computing worst-case bounds, proving statistical consistency.
Improved LSTM cell for high-frequency trading forecasts.
problem Precise stock price forecasting with minimal lags.
method Revised long short-term memory (LSTM) cell with optimal gate/state selection.
result Lower forecasting error compared to other recurrent neural networks.
Batched Neural Bandits reduces policy updates in sequential decision-making.
problem Sequential decision-making with batched policy changes.
method BatchNeuralUCB algorithm combining neural networks and optimism.
result Achieves similar regret as fully sequential version with fewer policy updates.
Over the past few years, the multi-armed bandit model has become increasingly popular in the machine learning community, partly because of applications including online content optimization. This paper reviews two different sequential learning tasks that have been considered in the bandit literature ; they can be formu…
This study optimizes covariate density and propensity score for efficient ATE estimation.
problem Efficiently estimating average treatment effects (ATEs) with minimal variance.
method Adaptive experiment optimizing both covariate density and propensity score.
result Proposed method minimizes the semiparametric efficiency bound for ATE estimation.
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.
Study improves neural network performance in sequential learning for image classification.
problem Improving neural network performance in sequential learning for image classification.
method Evaluation of approaches for computing prequential description lengths, proposing forward-calibration and replay-streams.
result Improved description lengths for image classification datasets, outperforming previous results.
We propose and analyze sequential design methods for the problem of ranking several response surfaces. Namely, given L ≥ 2 L \ge 2 L ≥ 2 response surfaces over a continuous input space X \cal X X , the aim is to efficiently find the index of the minimal response across the entire X \cal X X . The response surfaces are not known and ha…
New method improves variational inference for better posterior approximation.
problem Challenges in minimizing inclusive KL divergence for amortized variational inference.
method Likelihood-tempered sequential Monte Carlo samplers to estimate inclusive KL gradient.
result SMC-Wake method fits variational distributions more accurately than existing methods.
Online learning algorithms have impressive convergence properties when it comes to risk minimization and convex games on very large problems. However, they are inherently sequential in their design which prevents them from taking advantage of modern multi-core architectures. In this paper we prove that online learning …