The paper analyzes sampling efficiency of discrete diffusion models, providing sharp and adaptive guarantees.
problem Theoretical foundations of discrete diffusion models, especially sampling efficiency.
method Continuous-time Markov chain (CTMC) formulation, τ τ τ -leaping-based samplers, effective total correlation. result The τ τ τ -leaping algorithm achieves an iteration complexity of order i l d e O ( d / ε ) ilde O(d/\varepsilon) i l d e O ( d / ε ) for uniform discrete diffusion, improving existing bounds by a factor of d d d . Algorithm recovers graph from Glauber dynamics trajectory without mixing.
problem Learning Gaussian graphical models from a single Glauber dynamics trajectory.
method Three components: conditional variance estimation, pairwise influence test, robust median aggregation.
result Polynomial-time recovery of conditional independence graph from a single trajectory.
Open problem seeks an online learning algorithm for binary classification.
problem Existence of an online learning algorithm for binary classification with sublinear mistakes.
method Assumption of sequence allowing learning algorithm's existence.
result Specific condition determines sequence's learnability.
Extends tracking guarantees for time-varying variational inequalities.
problem Tracking solutions of time-varying variational inequalities.
method Extends existing results to sublinear solution paths and periodic problems.
result Discrete dynamical systems of periodic time-varying VI can exhibit chaotic behavior or converge to the solution.
We give a proof of the sublinear tracking property for sample paths of random walks on various groups acting on spaces with hyperbolic-like properties. As an application, we prove sublinear tracking in Teichmueller distance for random walks on mapping class groups, and on Cayley graphs of a large class of finitely gene…
Inference in log-linear models scales linearly in the size of output space in the worst-case. This is often a bottleneck in natural language processing and computer vision tasks when the output space is feasibly enumerable but very large. We propose a method to perform inference in log-linear models with sublinear amor…
LIBO optimizes repeated bandit tasks without prior knowledge or regret.
problem Optimizing repeated bandit tasks without prior knowledge or regret.
method LIBO sequentially meta-learns a kernel to adapt to the environment and solve tasks with the latest estimate.
result LIBO achieves sublinear lifelong regret, converging to oracle performance as more tasks are solved.
We investigate the problems of identity and closeness testing over a discrete population from random samples. Our goal is to develop efficient testers while guaranteeing Differential Privacy to the individuals of the population. We describe an approach that yields sample-efficient differentially private testers for the…
New sublinear sketches improve ANN and KDE for massive data streams.
problem Efficiently approximate nearest neighbors and kernel density estimation in large datasets.
method Developed sublinear space and query time algorithms for ANN and A-KDE in streaming and sliding-window models.
result Achieved near-optimal trade-offs between memory size and approximation error for ANN.
New algorithm for reinforcement learning in uncertain environments with unknown thresholds.
problem Safety in reinforcement learning in unknown and uncertain environments.
method Growing-Window estimator sampling and Stochastic Pessimistic-Optimistic Thresholding (SPOT) algorithm.
result Achieves sublinear regret and constraint violation of i l d e O ( T ) ilde{\mathcal{O}}(\sqrt{T}) i l d e O ( T ) . The paper shows how to learn causal representations with few environments and finite samples.
problem Learning causal representations from limited data and environments.
method Explicit, finite-sample guarantees with a logarithmic number of interventions.
result Consistent recovery of latent causal graph, mixing matrix, and unknown intervention targets.
Study efficient policy value estimation with sublinear samples.
problem Estimating optimal policy value in stochastic disjoint linear bandits.
method Sublinear sample estimation of optimal policy value.
result Achieves near optimal estimation error with sublinear samples.
We provide a general construction of time-consistent sublinear expectations on the space of continuous paths. It yields the existence of the conditional G-expectation of a Borel-measurable (rather than quasi-continuous) random variable, a generalization of the random G-expectation, and an optional sampling theorem that…
We consider the non-stochastic version of the (cooperative) multi-player multi-armed bandit problem. The model assumes no communication at all between the players, and furthermore when two (or more) players select the same action this results in a maximal loss. We prove the first T \sqrt{T} T -type regret guarantee for th…
Study tackles nonlinear factor models with unknown monotone links from incomplete and noisy data.
problem Learning nonlinear factor models with unknown monotone links from incomplete and noisy data.
method Formulated as joint recovery of low-rank factors, loadings, and nonlinear link function; proposed BCD algorithm with regularization.
result Established convergence guarantees and sublinear regret bounds for link-function updates.
LaPSRL achieves optimal regret for isoperimetric RL distributions.
problem Designing RL algorithms with sublinear regret for non-log-concave distributions.
method Posterior Sampling (PSRL) and Langevin sampling (LaPSRL) for isoperimetric distributions.
result LaPSRL achieves order-optimal regret and subquadratic complexity.
New algorithms for constrained online optimization with memory and predictions.
problem Control of constrained dynamical systems and scheduling with reconfiguration budgets.
method Proposed algorithms achieving sublinear regret and constraint violation under time-varying constraints, both with and without predictions.
result First algorithms achieving sublinear regret and constraint violation in constrained online optimization with memory.
We develop efficient algorithms to train ℓ 1 \ell_1 ℓ 1 -regularized linear classifiers with large dimensionality d d d of the feature space, number of classes k k k , and sample size n n n . Our focus is on a special class of losses that includes, in particular, the multiclass hinge and logistic losses. Our approach combines several…
New approach tackles resource constraints in bandit problems with weakly adaptive algorithms.
problem Maximizing rewards while adhering to general long-term constraints.
method Weakly adaptive primal and dual regret minimizers.
result Achieves sublinear constraints violations and competitive ratios in both stochastic and adversarial settings.
BILBO optimizes bilevel problems without repeated lower-level optimizations.
problem Challenges in bilevel optimization, especially in noisy, constrained, and derivative-free settings.
method BILevel Bayesian Optimization (BILBO) that optimizes both levels simultaneously, using confidence-bounds and function query selection.
result Theoretical and empirical evidence of BILBO's effectiveness on various problems.
Sequential screening and dynamic regret in multi-armed bandits with arriving arms
problem Sequential experimentation with expanding arm set
method UCB-AA with preliminary screening
result Regret bounds depend on arrival process
Algorithm achieves logarithmic regret with sublinear hints.
problem Online linear optimization with limited hints.
method Using logarithmic hints to improve regret from sqrt(T) to log(T).
result O(log T) regret with O(sqrt(T)) hints, and O(sqrt(T)) regret with o(sqrt(T)) hints.
Study shows how repetition affects learning in bandit settings, providing algorithms with sublinear regret.
problem Effect of persistence of engagement on learning in stochastic multi-armed bandit settings.
method Novel algorithms that achieve sublinear regret under temporal constraints.
result Additive effect of priming on regret upper bound, matching popular algorithms in absence of priming.
Quantum algorithm speeds up Gibbs partition function estimation.
problem Estimating partition functions in sublinear time.
method Sublinear-time quantum algorithm using quantum phase and amplitude estimation.
result First sublinear-time speed-up for partition function estimation.
The paper tackles estimating optimal policy value in linear bandits with general context distributions.
problem Estimating the optimal policy value in linear bandits with general context distributions.
method The paper provides lower bounds and an algorithm for sublinear estimation of V ∗ V^* V ∗ under stronger assumptions. result A practical algorithm that estimates a problem-dependent upper bound on V ∗ V^* V ∗ with O ~ ( d ) \widetilde{\mathcal{O}}(\sqrt{d}) O ( d ) samples. New algorithm optimizes functions in Matérn kernel RKHS with noisy feedback.
problem Optimizing functions in RKHS of Matérn kernel with noisy bandit feedback.
method π-GP-UCB algorithm with guaranteed sublinear regret for all ν > 1 and d ≥ 1.
result First practical approach with guaranteed sublinear regret for all ν > 1 and d ≥ 1.
New algorithm achieves sublinear regret in CMDPs without error cancellations.
problem Safety constraints in reinforcement learning with error cancellations.
method Model-based primal-dual algorithm for CMDPs with multiple constraints.
result Achieves sublinear regret without error cancellations.
Sublinear functionals of random variables are known as sublinear expectations; they are convex homogeneous functionals on infinite-dimensional linear spaces. We extend this concept for set-valued functionals defined on measurable set-valued functions (which form a nonlinear space), equivalently, on random closed sets. …
New data structure identifies close match from multiple distributions.
problem Identify the closest distribution to a given sample.
method Developed a sublinear-time data structure for identifying the closest distribution.
result First data structure that identifies the closest distribution in sublinear time.
Two-stage mechanism designs reduce regret in recommender systems with stochastic covariates.
problem Designing effective recommender systems with user covariates sampled online.
method Two-stage algorithm integrating incentivized exploration with offline learning methods.
result Achieves sublinear regret while maintaining incentive compatibility.
New framework finds periodic policies in reset-free MDPs with sublinear regret.
problem Reset-free reinforcement learning with unknown dynamics and terminal law constraints.
method Periodic framework, periodic policies, periodic regret.
result First non-asymptotic guarantees for reset-free learning in multi-agent settings.
Posterior sampling-based EI achieves sublinear regret bounds for expensive function optimization.
problem Theoretical analysis of expected improvement (EI) in Bayesian optimization.
method Randomized posterior sampling of EI.
result Achieves sublinear Bayesian cumulative regret bounds.
The study examines property testing and estimation under non-identically distributed samples, finding necessary and sufficient sample complexities.
problem Property testing and estimation under non-identically distributed samples.
method Analysis of distributional property testing and estimation in settings with heterogeneous entities.
result Necessary and sufficient sample complexities for property testing and estimation under non-identically distributed samples.
New algorithms reduce rejection sampling complexity for shape-constrained distributions.
problem Generating exact samples from shape-constrained distributions efficiently.
method Sublinear query complexity algorithms for rejection sampling.
result Sublinear complexity algorithms for sampling from shape-constrained distributions.
Greedy algorithm achieves sublinear regret for various distributions.
problem Efficient performance of greedy algorithms in linear contextual bandit problems.
method Introduced Local Anti-Concentration (LAC) condition to ensure sublinear regret.
result Greedy algorithm achieves O ( poly log T ) O(\operatorname{poly} \log T) O ( poly log T ) cumulative expected regret. Online learning algorithms are designed to learn even when their input is generated by an adversary. The widely-accepted formal definition of an online algorithm's ability to learn is the game-theoretic notion of regret. We argue that the standard definition of regret becomes inadequate if the adversary is allowed to a…
Online distributional prediction with latent cluster geometry
problem Predicting the full data-generating distribution in non-stationary streams
method Representing candidate laws as latent cluster geometry and using Gibbs quasi-posterior
result Achieving sublinear cumulative Wasserstein regret under bounded support and stable latent geometry
New algorithms sample spike-and-slab priors efficiently in high dimensions.
problem Sampling from spike-and-slab priors in high-dimensional settings.
method Provably efficient algorithms for posterior sampling with sublinear measurement count.
result First provable algorithms for spike-and-slab posterior sampling without strong SNR assumptions.
DR-RPO optimizes robust policies in RL with limited interaction, achieving sublinear regret.
problem Policy optimization in RL under distribution shift and adversarial dynamics.
method DR-RPO algorithm incorporating reference-policy regularization and upper confidence bonus for exploration.
result DR-RPO achieves sublinear regret and polynomial suboptimality bounds in robust RL.
New method reduces linear regret in high-dimensional bandit problems.
problem Heavy spectral tails in streaming matrices lead to linear regret in sketch-based linear bandits.
method Dyadic Block Sketching, a multi-scale matrix sketching approach.
result Achieves sublinear regret bounds without prior knowledge of streaming matrix properties.
New algorithm tackles delayed feedback in Lipschitz bandits with sublinear regret.
problem Delayed feedback in Lipschitz bandits.
method Design of algorithms for bounded and unbounded stochastic delays.
result Sublinear regret guarantees for both bounded and unbounded delays.
Two algorithms improve GP bandits by selecting priors and minimizing regret.
problem Selecting appropriate GP priors for unknown functions.
method Developed two algorithms: Prior-Elimination GP-TS and HyperPrior GP-TS.
result Established sublinear regret bound for HyperPrior GP-TS.
The paper shows how sublinear biLipschitz equivalences affect Morse boundaries of metric spaces.
problem Understanding how sublinear biLipschitz equivalences affect Morse boundaries of metric spaces.
method Defining sublinear biLipschitz equivalence and Morse boundaries, proving invariance under SBEs, using sublinear rays.
result κ-Morse boundaries of proper geodesic metric spaces are invariant under suitable sublinear biLipschitz equivalences.
New algorithms improve efficiency in learning from personalized rewards.
problem Learning from personalized rewards in recommendation systems.
method Developed provably efficient algorithms with sublinear regret for context-dependent feedback.
result Introduced a Lipschitz reward estimator that improves generalization performance.
Algorithm minimizes regret and converges to equilibria in Markov games.
problem Regret minimization and convergence to equilibria in general-sum Markov games under adversarial opponents.
method Decentralized algorithm that uses policy optimization and controls path length to achieve sublinear regret.
result Sublinear regret guarantees for convergence to correlated equilibrium in Markov games.
GP-PSRL achieves sublinear regret for continuous control with unbounded state space.
problem Analyzing regret bounds for GP-PSRL in continuous control with unbounded state space.
method Recursive application of Borell-Tsirelson-Ibragimov-Sudakov inequality and chaining method.
result Sublinear regret bound of O ~ ( H γ T T ) \widetilde{\mathcal{O}}(H\sqrt{γ_TT}) O ( H γ T T ) for GP-PSRL. Stochastic (sub)gradient methods require step size schedule tuning to perform well in practice. Classical tuning strategies decay the step size polynomially and lead to optimal sublinear rates on (strongly) convex problems. An alternative schedule, popular in nonconvex optimization, is called \emph{geometric step decay…
Simplifies and optimizes learning from untrusted batches with structure.
problem Learning from untrusted batches with potential structure.
method Synthesizes techniques from JO19 and CLM19, using Haar wavelets and soft filtering.
result Achieves sublinear sample complexity with polynomial time complexity.