Improved CEM for fast real-time planning in high-dimensional control tasks.
problem Sampling inefficiency of CEM in real-time planning.
method Novel additions to CEM including temporally-correlated actions and memory.
result 2.7-22x less samples and 1.2-10x performance increase.
A/B testing improves marketing decisions by selecting effective stratification variables.
problem Improving the sensitivity of A/B testing through stratified sampling.
method Designing an algorithm to select a subset of stratification variables for variance reduction.
result The subset selection method outperforms other variance reduction techniques in A/B testing.
TSAC achieves optimal frequentist regret in adaptive control of LQRs.
problem Adaptive control of stabilizable linear-quadratic regulators with unknown dynamics.
method Thompson Sampling (TS) for adaptive control of LQRs, with a novel early exploration strategy.
result Achieves i l d e O ( T ) ilde O(\sqrt{T}) i l d e O ( T ) regret, optimal for multidimensional systems. Study nonparametric estimator for Markov chain transition matrices in offline setting.
problem Estimating transition matrices of finite controlled Markov chains from logged data.
method Developed sample complexity bounds and conditions for minimaxity.
result Achieving certain statistical risk requires balancing mixing properties and sample size.
We consider the exploration-exploitation tradeoff in linear quadratic (LQ) control problems, where the state dynamics is linear and the cost function is quadratic in states and controls. We analyze the regret of Thompson sampling (TS) (a.k.a. posterior-sampling for reinforcement learning) in the frequentist setting, i.…
This paper tackles adaptive control of unknown Markov jump systems with sample complexity and regret bounds.
problem Adaptive control of unknown Markov jump systems with changing dynamics.
method Identification-based adaptive control using a system identification algorithm and certainty equivalent control.
result The proposed adaptive control scheme achieves O ( T ) \mathcal{O}(\sqrt{T}) O ( T ) regret, improving to O ( p o l y l o g ( T ) ) \mathcal{O}(polylog(T)) O ( p o l y l o g ( T )) with partial knowledge. New RL algorithms improve control tasks with data reuse.
problem Real-world control requires performance guarantees and data efficiency.
method Generalized Policy Improvement combining on-policy guarantees and sample reuse.
result Extensive experimental analysis shows benefits of new algorithms.
Unified framework suppresses model bias in semi-supervised learning with decoupled sampling control.
problem Class imbalance in semi-supervised learning, especially with distributional mismatches.
method Unified framework SC-SSL with decoupled sampling control, explicit expansion capability, and adaptive sampling probabilities.
result Consistent and state-of-the-art performance across various benchmark datasets and distribution settings.
Control Contraction Metrics (CCMs) provide a nonlinear controller design involving an offline search for a Riemannian metric and an online search for a shortest path between the current and desired trajectories. In this paper, we generalize CCMs to Finsler geometry, allowing the use of non-Riemannian metrics. We provid…
The paper explores when linear system identification is hard or easy, especially for under-actuated systems.
problem Statistical hardness of learning linear systems, especially under-actuated or under-excited systems.
method Using tools from minimax theory and recent statistical tools for finite sample analysis of system identification.
result The controllability index of linear systems affects the sample complexity of identification, making some systems hard to learn.
Recently introduced generative adversarial network (GAN) has been shown numerous promising results to generate realistic samples. The essential task of GAN is to control the features of samples generated from a random distribution. While the current GAN structures, such as conditional GAN, successfully generate samples…
A communication-efficient method controls FDR in network settings.
problem Controlling FDR in networks with limited communication.
method Sample-and-Forward: a flexible procedure for multihop networks.
result Nodes can control FDR without sharing p-values, achieving power and FDR control.
A new framework for controllable generation of discrete masked models.
problem Efficient controllable generation of discrete data models.
method Plug-and-play framework based on importance sampling.
result Demonstrates versatility across multiple domains, including protein design.
A new search-control strategy improves Dyna's efficiency.
problem Improving sample efficiency in model-based reinforcement learning.
method Proposes a novel search-control strategy by sampling high frequency regions of the value function.
result Empirically shows that high frequency regions require more samples to approximate, suggesting a better search-control strategy.
Combines control variates and adaptive importance sampling for Monte Carlo integration.
problem Improving Monte Carlo integration accuracy with control variates and adaptive sampling.
method A quadrature rule combining control variates and adaptive importance sampling.
result Non-asymptotic bound on the probabilistic error of the procedure.
We present an embedding of stochastic optimal control problems, of the so called path integral form, into reproducing kernel Hilbert spaces. Using consistent, sample based estimates of the embedding leads to a model free, non-parametric approach for calculation of an approximate solution to the control problem. This fo…
New method controls FDR for sparse GLMs, identifying positive and negative relationships.
problem Sparse GLMs with high-dimensional data and varying sample size.
method Debiased-Lasso estimator and CLIME method for precision matrix estimation.
result Asymptotically controls directional FDR and FDV for sparse GLMs.
New methods optimize transport and sampling for neural networks.
problem Designing effective training losses for neural networks.
method Optimal transport and stochastic optimal control through Schrödinger bridge problem.
result Valid training losses can be designed with numerical advantages.
Model shows screening for infectious disease is hard but Thompson sampling works well.
problem Optimal screening policy for infectious diseases is hard to find.
method Stochastic-control model with Thompson sampling for optimal performance.
result Thompson sampling provides optimal performance guarantees in screening for infectious diseases.
A RL-based method adds conditional controls to pre-trained diffusion models.
problem Precise control over generated samples in diffusion models.
method Formulates the task as an RL problem, using a classifier and KL divergence as reward functions.
result Produces soft-optimal policies that maximize reward functions, enabling conditional sampling.
This paper tackles robust control of noisy systems with uncertain distributions.
problem Optimal control of sampled-data stochastic systems with multiplicative noise and distributional ambiguity.
method Develops a convex relaxation to handle the ``concave-max'' geometry and derives a probabilistic performance guarantee.
result Derives an explicit, non-asymptotic bound on the duality gap and proves robust viability conditions.
New findings on depth vs. width in neural networks, showing depth can improve learnability.
problem Understanding the role of depth in neural networks, especially when width is unbounded.
method Analyzing sample complexity for learnability in norm-controlled depth-2 and depth-3 ReLU networks.
result Depth can improve learnability of functions that are otherwise unlearnable with depth-2 networks.
A new approach models exploration in continuous-time RL using random measures.
problem Modeling exploration in continuous-time reinforcement learning.
method Random measure approach to control execution in continuous-time RL.
result Grid-sampling limit SDE can replace existing models for theoretical analysis and learning algorithms.
Study non-monotonic loss functions in CRC, achieving valid risk control with large calibration samples.
problem Non-monotonic loss functions in CRC, violating existing theory's monotonicity assumption.
method Finite grid selection, calibration sample size analysis, Lipschitz continuity, monotonicity, distribution shift.
result Valid CRC achieved with large calibration samples, optimal excess risk rate of log ( m ) / n \sqrt{\log(m)/n} log ( m ) / n . New model optimizes portfolios over multiple periods using predictive control.
problem Optimizing multi-period portfolios with risk and variance objectives.
method Model Predictive Control with Mean-Variance and Risk Parity.
result 30x faster and more robust solutions compared to single period models.
End-to-end algorithm for controlling bilinear systems with probabilistic noise.
problem Controlling bilinear systems with noisy data.
method Proposes an end-to-end algorithm using statistical learning theory and robust controller design.
result Derived finite sample identification error bounds and structurally suitable for control.
Optimal control theory connects diffusion models to generative modeling.
problem Sampling from unnormalized densities in statistics and computational sciences.
method Deriving a Hamilton-Jacobi-Bellman equation and applying control theory to minimize Kullback-Leibler divergence.
result Time-reversed diffusion sampler (DIS) outperforms other diffusion-based sampling methods.
New algorithm borrows future randomness to stabilize model-free control.
problem Double sampling problem in model-free control with nonlinear approximations.
method Borrowing from the future (BFF) algorithm to approximate re-sampling of next states.
result BFF is close to unbiased SGD under smooth dynamics, validated by simulations.
New method uses unlabeled data to estimate intercept in case-control logistic regression.
problem Estimating intercept in case-control logistic regression.
method Construct likelihood function, use iterative algorithm to find maximum likelihood estimator.
result Proposed method identifies intercept and improves estimation efficiency.
New method for sampling from multivariate distributions using optimal control and quantum mechanics.
problem Sampling from continuous multivariate probability distributions efficiently and accurately.
method Harmonic Path Integral Diffusion (H-PID) framework, formulated as a Stochastic Optimal Control problem.
result Efficient sampling algorithms without neural networks, revealing dynamic phase transitions.
Paper analyzes Greedy-GQ for reinforcement learning with Markovian noise.
problem Analyzing Greedy-GQ for reinforcement learning with Markovian noise.
method Develops finite-sample analysis for Greedy-GQ with linear function approximation under Markovian noise.
result Provides theoretical justification for choosing stepsizes for faster convergence.
Improved text generation with constraints using discrete auto-regressive biasing.
problem Balancing fluency and constraint satisfaction in LLM outputs.
method Discrete Auto-regressive Biasing, leveraging gradients in discrete text space.
result Significantly improved constraint satisfaction with comparable fluency.
Meta-reinforcement learning improves fault-adaptive control efficiency.
problem Adaptive control under abrupt system faults with strict time constraints.
method Model-agnostic meta learning (MAML) with a fault library of prior policies.
result Improved sample efficiency and quick adaptation to new faults.
Monte Carlo (MC) sampling algorithms are an extremely widely-used technique to estimate expectations of functions f(x), especially in high dimensions. Control variates are a very powerful technique to reduce the error of such estimates, but in their conventional form rely on having an accurate approximation of f, a pri…
We study Bayesian optimal control of a general class of smoothly parameterized Markov decision problems. Since computing the optimal control is computationally expensive, we design an algorithm that trades off performance for computational efficiency. The algorithm is a lazy posterior sampling method that maintains a d…
Proposes a new method to control FDR using frequentist-assisted horseshoe for high-dimensional testing.
problem Designing tests with frequentist false discovery rate control using horseshoe prior.
method Frequentist-assisted horseshoe procedure for high-dimensional normal means testing.
result Consistently achieves robust finite-sample FDR control in various sparse cases.
Improved confidence interval estimation with control variates.
problem Estimating confidence intervals with minimal samples.
method Designing an estimation algorithm using control variates and leveraging order statistics.
result Improved asymptotic efficiency compared to existing algorithms.
A new method models continuous-time counterfactual outcomes using neural controlled differential equations.
problem Estimating personalized healthcare outcomes over irregularly sampled data.
method Interpreting data as samples from a continuous-time process, modeling latent trajectory using controlled differential equations, and using adversarial training for time-dependent confounding.
result TE-CDE consistently outperforms existing approaches in irregularly sampled scenarios.
New method calibrates diffusion models for image regression tasks.
problem Ensuring reliability of diffusion models for critical applications.
method Risk-Controlling Prediction Sets (RCPS) with convex optimization.
result Calibrated entrywise intervals and risk control with minimal mean interval length.
Itô maps provide a method for any-step SDE integration.
problem Stochastic dynamics
method Itô map formulation
result Empirical results on synthetic and image-generation benchmarks
Paper tackles non-Markovian control problems with new learning methods.
problem Non-Markovian stochastic control problems with unknown parameters.
method Off-model training and importance sampling for deep neural network approximation.
result Quantitative error bounds for adaptive learning under model uncertainty.
Deep networks have enabled reinforcement learning to scale to more complex and challenging domains, but these methods typically require large quantities of training data. An alternative is to use sample-efficient episodic control methods: neuro-inspired algorithms which use non-/semi-parametric models that predict valu…
High-throughput 3D control training system achieves 100,000 FPS.
problem Lack of efficient, single-machine reinforcement learning systems.
method Sample Factory combines asynchronous sampling and off-policy correction.
result Achieves 100,000 FPS on 3D control problems without sacrificing sample efficiency.
In statistics and machine learning, approximation of an intractable integration is often achieved by using the unbiased Monte Carlo estimator, but the variances of the estimation are generally high in many applications. Control variates approaches are well-known to reduce the variance of the estimation. These control v…
Action-bisimulation learns long-horizon controllability for reinforcement learning.
problem Learning relevant state features in high-dimensional observations for robust reinforcement learning.
method Action-bisimulation encoding, inspired by bisimulation invariance, extends single-step controllability to multi-step.
result Action-bisimulation pretraining improves sample efficiency in various environments.
Jeffrey guidance extends diffusion-model control to more complex applications.
problem Controlling diffusion models beyond simple cases like conditional sampling.
method Leveraging Jeffrey's rule of conditioning to update marginal distributions towards a target distribution.
result Significant reductions in FID on CIFAR-10 and FFHQ with Inception embeddings as the target.
The paper provides guarantees for feedback control with sensor errors.
problem Certifying performance and safety in feedback control systems with sensor errors.
method Solving a supervised learning problem to characterize sensor errors and providing uniform error bounds.
result Finite-time convergence rate on sub-optimality of using a regressor in closed-loop for waypoint tracking.
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…