New theorem improves spectral gap for sampling from mixture distributions.
problem Sampling from multimodal distributions with simulated tempering.
method Introduced a decomposition theorem for the restricted spectral gap of simulated tempering.
result Lower bound on the restricted spectral gap for mixture distributions.
Study shows exponential gap in sample complexity between noisy and non-noisy recurrent neural networks.
problem Understanding the impact of noise on the sample complexity of recurrent neural networks.
method Analyzing noisy multi-layered sigmoid recurrent neural networks with independent noise and proving lower bounds.
result Exponential gap in sample complexity between noisy and non-noisy networks, even for small noise values.
Improved uniform convergence bound with fat-shattering dimension reduces sample complexity gap.
problem Gap between upper and lower bounds on sample complexity for fat-shattering dimension.
method Provided an improved uniform convergence bound.
result Closed the gap between existing upper and lower bounds on sample complexity.
This work analyzes the gap between off-policy and on-policy policy gradient methods and provides conditions to reduce this gap.
problem The gap between off-policy and on-policy policy gradient methods and conditions to reduce it.
method Theoretical analysis and empirical evidence of conditions to reduce the on-off gap.
result Conditions to reduce the on-off gap between off-policy and on-policy policy gradient methods.
New bounds show limitations of sample-wise information-theoretic generalization.
problem Limitations of sample-wise information-theoretic generalization bounds.
method Analysis of existing bounds and derivation of new bounds.
result No sample-wise information-theoretic bounds exist for expected squared generalization gap.
Let F be a family of Borel measurable functions on a complete separable metric space. The gap (or fat-shattering) dimension of F is a combinatorial quantity that measures the extent to which functions f in F can separate finite sets of points at a predefined resolution gamma > 0. We establish a connection between the g…
New offline RL method works with limited data and function approximators.
problem Sample efficiency with limited data and weak function approximators.
method Pessimistic algorithm based on version space formed by marginalized importance sampling (MIS), with gap assumption.
result Guarantees sample efficiency for simple algorithm under specific assumptions.
New methods reduce bias in estimating optimality gaps for risk-averse stochastic programs.
problem Optimality gap estimation bias in risk-averse stochastic programs.
method Two independent samples, each estimating a different component of the optimality gap.
result Our method reduces bias in estimating optimality gaps for risk-averse problems.
New bounds close the score matching gap for diffusion models.
problem The difference between sample quality and score matching loss in diffusion models.
method Theoretical analysis of score matching gap, developing tighter bounds for KL divergence, reverse KL divergence, and Wasserstein distance.
result The quality of score approximation impacts closing the score matching gap for low noise scales.
New algorithm reduces sample complexity for planning in MDPs.
problem Planning in MDPs with unknown transitions.
method MDP-GapE, a trajectory-based MCTS algorithm.
result Proves upper bound on sample complexity in terms of sub-optimality gaps.
In the classical best arm identification (Best-1-Arm) problem, we are given n stochastic bandit arms, each associated with a reward distribution with an unknown mean. We would like to identify the arm with the largest mean with probability at least 1−δ, using as few samples as possible. Understanding the sample c…
UCB algorithm's arm-sampling behavior is revealed, leading to new insights and proofs.
problem Optimizing multi-armed bandit algorithms for worst-case scenarios.
method Analysis of UCB algorithm's arm-sampling behavior and process-level characterization.
result UCB's arm-sampling rates are asymptotically deterministic, regardless of problem complexity.
Extracurricular learning closes the accuracy gap in knowledge distillation.
problem Accuracy gap between teacher and student models after knowledge distillation.
method Modeling student and teacher output distributions, sampling from an extended data distribution, and matching over this set.
result Extracurricular learning reduces the accuracy gap by 46% to 68%.
Study best arm identification with contextual info, achieving optimal misidentification probability.
problem Identify the best treatment arm with minimal misidentification probability in a small gap scenario.
method Developed RS-AIPW strategy that matches lower bound of misidentification probability in the small-gap regime.
result RS-AIPW strategy is asymptotically optimal for best arm identification.
The paper examines how sampling data affects the performance of submodular maximization.
problem Performance loss due to probability sampling in submodular maximization.
method Examines a simple probability sampling method where each data point is selected with probability at least r.
result The sampling gap is both upper and lower bounded by 1/r for policywise submodular utility functions.
New study shows exponential lower bound for RL even with constant suboptimality gap.
problem Can RL be sample-efficient with a constant suboptimality gap?
method Analyzes reinforcement learning in the online setting with a linearly realizable optimal Q-function.
result An exponential sample complexity lower bound still holds even with a constant suboptimality gap.
The paper improves tensor completion bounds using spectral gap.
problem Theoretical limitations in tensor completion, especially for deterministic sampling.
method Bounding the generalization error of tensor completion methods using spectral gap.
result Improved bounds on tensor completion error, reducing rank dependence.
This paper studies the problem of adaptively sampling from K distributions (arms) in order to identify the largest gap between any two adjacent means. We call this the MaxGap-bandit problem. This problem arises naturally in approximate ranking, noisy sorting, outlier detection, and top-arm identification in bandits. Th…
Improved sample complexity for Gaussian Mixture Models using Pair Correlation Factor.
problem Understanding the sample complexity of Gaussian Mixture Models.
method Introducing Pair Correlation Factor (PCF) to measure clustering of component means and improving sample complexity bounds.
result The Pair Correlation Factor (PCF) more accurately determines the difficulty of parameter recovery in Gaussian Mixture Models.
We consider the problem of estimating from sample paths the absolute spectral gap γ∗ of a reversible, irreducible and aperiodic Markov chain (Xt)t∈N over a finite state space Ω. We propose the UCPI (Upper Confidence Power Iteration) algorithm for this problem, a low-complexity algorithm …
BITS for GAPS uses Bayesian methods to improve surrogate model accuracy in complex systems.
problem Improving surrogate model accuracy in complex physical systems with uncertainty.
method Bayesian Information-Theoretic Sampling for hierarchical Gaussian Process Surrogates.
result Increased expected information gain and predictive accuracy by targeting high-uncertainty regions.
Data augmentation by mixing samples, such as Mixup, has widely been used typically for classification tasks. However, this strategy is not always effective due to the gap between augmented samples for training and original samples for testing. This gap may prevent a classifier from learning the optimal decision boundar…
New technique reduces imitation learning performance gap in finite samples.
problem Imitation learning performance gap in finite samples.
method Replay estimation to reduce empirical variance in finite samples.
result Achieves optimal performance gap of $\widetilde{O} \left( \min({H^{3/2}} / {N}, {H} / {\sqrt{N}}
ight)$.
Federated learning studies separate client data and distribution gaps.
problem Understanding performance differences in federated learning across different datasets.
method Proposed a framework to disentangle out-of-sample and participation gaps.
result Dataset synthesis strategy is crucial for realistic simulations of federated learning generalization.
Estimates covariance matrices using Markov chain Monte Carlo with improved sample complexity.
problem Complexity of covariance matrix estimation for Gibbs distributions.
method Uses Markov chain Monte Carlo with conditions on the chain's spectral gap and Poincaré inequality.
result Achieves similar sample complexity as i.i.d. samples with better query complexity.
The effectiveness of model-based versus model-free methods is a long-standing question in reinforcement learning (RL). Motivated by recent empirical success of RL on continuous control tasks, we study the sample complexity of popular model-based and model-free algorithms on the Linear Quadratic Regulator (LQR). We show…
Improved online Q-learning for MDPs with concentration bounds.
problem Online Q-learning in infinite-horizon discounted MDPs with sublinear regret for large gaps.
method Smoothed εn-Greedy exploration scheme combining εn-greedy and Boltzmann exploration, analyzed using concentration bounds for contractive Markovian stochastic approximation. result Near-ildeO(N9/10) regret bound for Smoothed εn-Greedy exploration scheme. Paper tackles sample-efficient RL for linearly realizable MDPs with limited revisiting.
problem Sample-efficient reinforcement learning for linearly realizable MDPs with limited revisiting.
method Develops a new sampling protocol that allows for backtracking and revisiting states in a controlled manner.
result Achieves polynomial sample complexity scaling with feature dimension, horizon, and inverse sub-optimality gap.
New algorithm identifies good arms with fewer samples when thresholds are close.
problem Good arm identification in bandit problems with small threshold gaps.
method Proposes lil'HDoC algorithm to improve GAI under small threshold gaps.
result Sample complexity of first λ output arm is nearly identical to HDoC algorithm when thresholds are close.
Improved gap-dependent bounds for reinforcement learning with linear approximations.
problem Achieving nearly minimax-optimal performance with linear function approximation.
method Developed and analyzed the LSVI-UCB++ algorithm and its concurrent variant.
result First gap-dependent regret bound for nearly minimax-optimal algorithm LSVI-UCB++.
Unified framework for causal inference under sample selection.
problem Causal inference under sample selection with treatment and outcome non-randomness.
method ForestRiesz estimator, Riesz representation framework.
result ForestRiesz estimator yields more stable treatment effect estimates than conventional double machine learning approaches.
Machine learning's predictive power is limited by sample size, as shown by the Limits-to-Learning Gap.
problem The limitations of machine learning in approximating true data-generating processes.
method Characterization of a universal lower bound (LLG) quantifying the discrepancy between empirical fit and population benchmark.
result Standard ML approaches can substantially understate true predictability in financial data.
New method identifies Condorcet winner in dueling bandits with improved sample complexity.
problem Identifying Condorcet winner in noisy pairwise comparisons.
method Exploits full gap matrix Δ to improve sample complexity.
result Improves sample complexity guarantees by leveraging informative comparisons.
Attributing forecast gaps to component models in complex model suites
problem Attributing forecast gaps between model-suite forecasts and realized outcomes
method Formalizing walk analysis and adapting order-independent attribution frameworks
result Deriving efficient formulas for elementwise and vectorized gap attribution
Characterizes UCB algorithm performance in bandit problems.
problem Optimizing UCB algorithm performance in stochastic bandit environments.
method Novel perturbation analysis to characterize CLT of pulls and means.
result Smooth interpolation of pseudo-regret between large and small gap regimes.
Improved spectral gap for MwG with adaptive RWM proposals.
problem Improving mixing efficiency of MwG for log-concave distributions.
method Using adaptive RWM proposals tuned to match conditional variances of log-concave target distributions.
result Established a spectral gap lower bound of order O(1/κd) for MwG. The paper tackles attributing forecast gaps in complex model suites.
problem Attributing forecast gaps to individual component models in complex model suites.
method Formalized walk analysis, adapted LMDI and Shapley value approaches.
result Developed efficient formulas for gap attribution in practical portfolio-scale examples.
Study shows gap between uniform convergence and test error in random feature models.
problem Understanding the gap between uniform convergence and test error in random feature models.
method Analytical expressions for uniform convergence over norm balls, interpolators, and minimum norm interpolator risk derived and proved.
result Uniform convergence over interpolators still gives a non-trivial bound of test error even when classical uniform convergence is vacuous.
Paper introduces a method to control early classification accuracy gaps.
problem Maintaining accuracy in early classification without full input processing.
method Statistical framework for a calibrated stopping rule.
result Reduces up to 94% of timesteps while controlling accuracy gaps.
New research shows some distributions hard to sample via diffusions.
problem Some distributions hard to sample via diffusions.
method Learning drifts of diffusions to approximate target distributions.
result Superpolynomially close drifts can yield very far approximations.
Polynomial-time algorithm finds planted hypercube vectors in Gaussian mixtures.
problem Clustering d-dimensional Gaussian mixtures with unknown covariance.
method Lattice-based methods using Lenstra--Lenstra--Lovasz reduction.
result Achieves statistically-optimal sample complexity of d+1 samples.
This paper tackles learning Stackelberg equilibrium in asymmetric games efficiently from noisy samples.
problem Learning Stackelberg equilibrium in asymmetric, general-sum games efficiently from noisy samples.
method The paper initiates the theoretical study of sample-efficient learning of the Stackelberg equilibrium in bandit feedback setting.
result Sharp positive results on sample-efficient learning of Stackelberg equilibrium with value optimal up to a fundamental gap identified.
Improved lower bound for parallel tempering's mixing time.
problem Slow convergence and mixing in multimodal target distributions.
method Presented a new lower bound for the spectral gap of parallel tempering.
result Improved the best existing bound on spectral gap with polynomial dependence on parameters.
In this paper, we propose several improvements on the block-coordinate Frank-Wolfe (BCFW) algorithm from Lacoste-Julien et al. (2013) recently used to optimize the structured support vector machine (SSVM) objective in the context of structured prediction, though it has wider applications. The key intuition behind our i…
Two new algorithms solve privacy-constrained SVI and SSP problems.
problem Privacy-constrained stochastic variational inequality and saddle-point problems.
method Proposed Noisy Stochastic Extragradient (NSEG) and Noisy Inexact Stochastic Proximal Point (NISPP) algorithms.
result Optimal risk bounds for weak gap function with sampling with replacement.
Study quantile multi-armed bandits for identifying the best arm with a specified quantile level.
problem Identifying the arm with the highest quantile in multi-armed bandits with private rewards.
method Proposed a (non-private) and differentially private successive elimination algorithms for best-arm identification.
result The proposed algorithms are essentially optimal for quantile bandit problems, with finite sample complexity even for distributions with infinite support-size.
Improves Bayesian predictive performance in misspecified models.
problem Misspecification gap between inferential and predictive risks.
method Develops a multi-sample loss (PACm) to bridge the gap. result Empirical study shows improved predictive distribution.
New research shows that the dimension gap between intrinsic and ambient dimensions affects adversarial vulnerability of machine learning models.
problem The mystery of adversarial attacks on machine learning models.
method Introducing two types of adversarial attacks and proving their relationship to the dimension gap.
result The dimension gap between intrinsic and ambient dimensions makes clean-trained models more vulnerable to off-manifold adversarial perturbations.