Algorithm minimizes regret while adhering to unknown safety constraints.
problem Online learning with unknown safety constraints.
method General meta-algorithm leveraging online regression and learning oracles.
result Concrete algorithm with T \sqrt{T} T regret for linear constraints. Optimal algorithm for contextual bandits with unknown context distributions.
problem Designing efficient algorithms for contextual bandits with unknown context distributions.
method Cross-learning setting, novel technique for coordinating multiple epochs.
result Nearly tight regret bound of O ~ ( T K ) \widetilde{O}(\sqrt{TK}) O ( T K ) for learning to bid in first-price auctions and sleeping bandits. We develop an unsupervised, nonparametric, and scalable statistical learning method for detection of unknown objects in noisy images. The method uses results from percolation theory and random graph theory. We present an algorithm that allows to detect objects of unknown shapes and sizes in the presence of nonparametri…
Proposes a new method to find overconfident predictions in classifiers.
problem Challenges in assessing classifier accuracy without labeled test data.
method Facility locations utility model and greedy query algorithm.
result Greedy query algorithm finds overconfident unknown unknowns more effectively.
Efficient algorithm for unknown linear systems with convex costs.
problem Controlling an unknown linear system with stochastic convex costs.
method Optimism in the Face of Uncertainty paradigm.
result Achieves optimal T \sqrt{T} T regret-rate. Polynomial-time algorithms improve on isotonic matrix estimation with unknown permutations.
problem Estimating a bivariate isotonic matrix with unknown permutations from noisy observations.
method Design and analysis of polynomial-time algorithms.
result Minimax optimal, computationally efficient estimation achievable in certain settings.
Algorithm learns similarities to optimize bandit decisions in unknown metric space.
problem Optimizing decisions in unknown metric space with nonparametric reward functions.
method Data-driven similarities for adaptive partitioning of context-arm space.
result Regret bounds highlight algorithm's dependence on reward functions' local geometry.
New algorithms learn graphons in GMFGs without knowing them.
problem Learning graphons in Graphon Mean-Field Games with unknown graphons.
method Proximal Policy Optimization for GMFG (GMFG-PPO) and kernel embedding methods for estimating graphons.
result The proposed algorithms reduce exploitability when learning unknown graphons.
New algorithms estimate unknown training examples to improve ML model generalization.
problem Distribution shift between training and testing data leads to poor generalization.
method Combining species-estimation techniques with data-driven methods.
result Correcting the training set with unknown examples improves model robustness.
Algorithm estimates Gaussian parameters under unknown truncation sets.
problem Estimating Gaussian parameters when samples are truncated to unknown sets.
method Efficient algorithm for arbitrary unknown truncation sets, using Gaussian surface area as complexity measure.
result Algorithm works for large families of sets including intersections of halfspaces and general convex sets.
This paper tackles unknown causal graphs and soft interventions, establishing regret bounds and an efficient algorithm.
problem Designing causal bandit algorithms with unknown causal graphs and stochastic intervention models.
method Establishes novel regret bounds and presents a computationally efficient algorithm for unknown graph and soft interventions.
result Regret bounds for unknown graph and soft interventions, with a universal minimax lower bound.
Bayesian optimisation algorithm for unknown search spaces with sub-linear regret.
problem Efficient optimisation of expensive black-box functions in unknown search spaces.
method Expands search space over iterations based on a hyperharmonic series, scales to high dimensions.
result Sub-linear regret growth for both algorithms.
New algorithms achieve logarithmic regret in learning linear quadratic control systems.
problem Learning in Linear Quadratic Control systems with unknown parameters.
method Efficient algorithms for two scenarios: unknown A A A or B B B with certain conditions. result Regret scales logarithmically with the number of steps, not square root.
New algorithm detects changes in Markov kernels with unknown post-change kernel.
problem Detecting changes in Markov kernels with unknown post-change kernel.
method Developed a new change detection algorithm assuming uniform ergodicity.
result Derived upper and lower bounds on mean delay and time between false alarms.
New algorithm controls systems with unknown, changing losses.
problem Control systems with adversarial perturbations and unknown loss function.
method Efficient sublinear regret algorithm for bandit convex optimization with memory.
result Achieves efficient control with sublinear regret in the presence of unknown, changing losses.
Algorithm learns mixtures of rankings from noisy data.
problem Learning an unknown mixture of rankings from noisy samples.
method Algorithm for different noise models, including heat kernel and Mallows model.
result High accuracy learning of mixture to n O ( log k ) n^{O(\log k)} n O ( l o g k ) time. New algorithm POO optimizes noisy, unknown-smooth functions.
problem Optimizing functions with unknown smoothness and noisy evaluations.
method Adaptive optimization algorithm POO.
result POO performs nearly as well as known algorithms with smoothness knowledge, and works for broader classes of functions.
No-regret BO algorithm adapts hyperparameters to optimize unknown functions.
problem Misspecification of hyperparameters in BO leads to poor local optima.
method Adapts hyperparameters online to expand function class and converge to optimum.
result First provably no-regret BO algorithm with unknown hyperparameters.
SaaS uses training speed to infer unknown labels in semi-supervised learning.
problem Inference of unknown labels in semi-supervised learning.
method Uses learning speed during stochastic gradient descent to infer unknown labels.
result Achieves state-of-the-art results in semi-supervised learning benchmarks.
Two algorithms for nonlinear systems with unknown inputs are compared and implemented.
problem Analysis and comparison of algorithms for nonlinear systems with unknown inputs.
method Two symbolic algorithms, ORC-DF and FISPO, are compared and implemented in a MATLAB toolbox.
result FISPO is more generally applicable, while ORC-DF is more efficient for affine input models.
Bayesian algorithm stabilizes unknown continuous-time systems from unstable data.
problem Learning and stabilizing unknown continuous-time systems with uncertain dynamics.
method Bayesian learning algorithm that learns from unstable data to stabilize the system in finite time.
result The algorithm stabilizes unknown continuous-time stochastic linear systems effectively after a short time period.
Study methods to recover unknown processes in PDEs from data.
problem Identifying unknown processes in time-dependent PDEs using observational data.
method Theoretical analysis and numerical approaches including Galerkin and collocation algorithms.
result The Galerkin algorithm is more suitable for practical situations with noisy data.
New algorithm achieves data-dependent regret bounds in MDPs with unknown transitions.
problem Achieving best-of-both-worlds guarantees with data-dependent regret bounds in MDPs with unknown transitions.
method Optimistic follow-the-regularized-leader algorithm with new optimistic Q-function estimators and transition bonus.
result First-order, second-order, and path-length bounds with polylog(T) regret in the stochastic regime.
New algorithms for generalized linear bandits with unknown reward functions.
problem Misspecification of reward functions in existing bandit algorithms.
method Introducing single index bandits, proposing STOR, ESTOR, and GSTOR algorithms.
result Achieved nearly optimal regret bound of i l d e O T ( T ) ilde{O}_T(\sqrt{T}) i l d e O T ( T ) . New algorithms handle unknown delays in online learning problems.
problem Handling unknown delays in bandit online learning.
method DEXP3 for MAB and DBGD for BCO, with a unified analysis.
result Regret bounds of O ( K d ˉ ( T + D ) ) {\cal O}\big( \sqrt{K\bar{d}(T+D)} \big) O ( K d ˉ ( T + D ) ) for DEXP3 and O ( K ( T + D ) ) {\cal O}\big( \sqrt{K(T+D)} \big) O ( K ( T + D ) ) for DBGD. Method preserves Hamiltonian structure for unknown systems from noisy data.
problem Reconstructing unknown Hamiltonian systems from trajectory data.
method Directly approximates the unknown Hamiltonian, enforcing conservation.
result Structure-preserving property demonstrated and effective in numerical examples.
Optimistic Thompson Sampling reduces regret in unknown multi-player games.
problem Navigating uncertainty in unknown multi-player games with strategic decision-making.
method Introduces Thompson Sampling algorithms that exploit opponents' actions and reward structures.
result Achieves over tenfold improvements in experimental budgets with logarithmic regret bound.
Efficient algorithm controls unknown systems with adversarial perturbations.
problem Controlling unknown linear systems with adversarial perturbations and convex losses.
method Measures regret against an optimal linear policy, provides efficient algorithm with sublinear regret bound.
result First efficient algorithm with sublinear regret bound of T^{2/3}.
New algorithm clusters streaming data efficiently.
problem Challenges in clustering streaming data.
method Online clustering algorithm for unknown number of clusters.
result Produces partitions close to full data clustering.
The paper tackles linear regression without knowing the correspondence between variables.
problem Linear regression without known correspondence between variables.
method The paper provides a fully polynomial-time approximation scheme and an efficient algorithm based on lattice basis reduction.
result The efficient algorithm can exactly recover the unknown linear function in arbitrary dimension.
We study statistical detection of grayscale objects in noisy images. The object of interest is of unknown shape and has an unknown intensity, that can be varying over the object and can be negative. No boundary shape constraints are imposed on the object, only a weak bulk condition for the object's interior is required…
New algorithm learns safe policies in unknown environments.
problem Learning safe policies in unknown, potentially unsafe environments.
method C-UCRL: Upper Confidence Reinforcement Learning for constrained MDPs.
result Achieves sub-linear regret while satisfying constraints.
New algorithm tackles stochastic bandits with unknown scale using kurtosis bounds.
problem Existing strategies for stochastic bandits require known scale parameters.
method Develops a scale-free algorithm for stochastic bandits with a bound on kurtosis.
result Generalizes results for Gaussian and uniform distributions to non-parametric setup.
Optimal resource allocation in censored semi-bandits with unknown thresholds.
problem Sequential resource allocation with unknown thresholds and hidden parameters.
method Established equivalence to MP-MAB and Combinatorial Semi-Bandits, derived optimal algorithms.
result Validated performance of proposed algorithms on synthetic data.
Efficient algorithm for learning MDPs with unknown transitions and bandit feedback.
problem Learning in episodic finite-horizon MDPs with unknown transitions and bandit feedback.
method Proposes an efficient algorithm with i l d e O ( L ∣ X ∣ ∣ A ∣ T ) \mathcal{ ilde{O}}(L|X|\sqrt{|A|T}) i l d e O ( L ∣ X ∣ ∣ A ∣ T ) regret. result Achieves i l d e O ( T ) \mathcal{ ilde{O}}(\sqrt{T}) i l d e O ( T ) regret, matching previous work with full-information feedback. New algorithms improve best-arm identification with varying rewards.
problem Identifying the best arm with varying reward variances in fixed budget.
method Proposed two algorithms: SHVar for known variances, SHAdaVar for unknown variances; uses non-uniform budget allocation.
result Bounding misidentification probabilities for both algorithms.
New algorithm recovers matrices with unknown correspondences.
problem Recovering matrices from observations with unknown correspondences.
method Solves a nuclear norm minimization problem via proximal gradient with a Max-Oracle.
result Achieves state-of-the-art performance and high accuracy in recovering ground-truth correspondences.
Proposes DGBR for stable predictions across unknown environments.
problem Stable predictions across unknown environments in machine learning.
method Joint optimization of a deep auto-encoder for feature selection and a global balancing model for stable prediction.
result Demonstrates stable predictions across unknown environments with empirical experiments.
New algorithm for competing influence spread in unknown networks.
problem Maximizing influence spread in a social network with unknown probabilities.
method Combinatorial multi-armed bandit (CMAB) framework, Triggering Probability Modulated (TPM) condition, OCIM-TS, OCIM-OFU, OCIM-ETC.
result Sublinear Bayesian and frequentist regret for OCIM-TS and OCIM-OFU, respectively.
New algorithm reduces dynamic regret for MDPs with unknown transition and adversarial rewards.
problem Episodic linear mixture MDPs with unknown transition and adversarial rewards.
method Combines occupancy-measure-based global optimization and policy-based variance-aware value-targeted regression.
result Achieves near-optimal dynamic regret of O ~ ( d H 3 K + H K ( H + P ˉ K ) ) \widetilde{\mathcal{O}}(d \sqrt{H^3 K} + \sqrt{HK(H + \bar{P}_K)}) O ( d H 3 K + H K ( H + P ˉ K ) ) . New classifiers tackle unknown classes with extreme value theory.
problem Classifiers struggle with unknown classes having different geometries.
method Proposes two new classifiers based on extreme value theory approximations.
result New classifiers outperform existing methods in simulations and real datasets.
Algorithm estimates common mean from Gaussian variables with unknown variances.
problem Estimating common mean from Gaussian variables with different unknown variances.
method Intuitive and efficient algorithm using Subset-of-Signals model as benchmark.
result Improved estimation error by polynomial factors compared to previous work.
Efficient algorithm reduces control system learning regret to sqrt(T).
problem Learning Linear-Quadratic Regulators with unknown dynamics efficiently.
method First computationally-efficient algorithm with sqrt(T) regret.
result Resolves open question on control system learning.
In the series of our earlier papers on the subject, we proposed a novel statistical hypothesis testing method for detection of objects in noisy images. The method uses results from percolation theory and random graph theory. We developed algorithms that allowed to detect objects of unknown shapes in the presence of non…
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.
New method for fair resource allocation in AI-aware networks with unknown utility functions.
problem Fair resource allocation in AI-aware communication networks with unknown utility functions.
method Distributed, data-driven bilevel optimization approach to learn surrogate utility functions.
result The proposed algorithm learns from data to autotune surrogate utility functions for unknown utility functions.
GP-MRO discovers robust mixed strategies for unknown objectives.
problem Optimizing unknown objectives against worst-case uncertain parameters.
method Sequential learning from noisy point evaluations, combining online learning and Gaussian processes.
result GP-MRO finds robust mixed strategies that significantly improve performance over deterministic strategies.
Paper develops PAC-Bayes bounds for unknown linear systems.
problem Learning controllers for unknown stochastic linear discrete-time systems.
method PAC-Bayes framework for data-dependent high probability bounds.
result Proposes efficient learning algorithms with theoretical guarantees.