Unified framework for model-based RL with sample complexity guarantees.
problem Designing efficient posterior sampling methods for model-based RL.
method Optimistic posterior sampling, Hellinger distance reduction, data likelihood measurement.
result Unified algorithms with state-of-the-art sample complexity guarantees.
Paper proposes a hybrid model-based and data-driven approach for one-bit compressive autoencoding.
problem Designing efficient one-bit compressive autoencoding models for complex systems.
method Hybrid model-based and data-driven methodology for one-bit sparse signal recovery.
result Significant improvement in one-bit compressive autoencoding compared to state-of-the-art algorithms.
New method designs experiments robustly for nonlinear estimation, improving parameter knowledge.
problem Designing robust experiments for nonlinear estimation under parametric uncertainty.
method Multi-stage robust optimization framework for sequential experiments.
result Identifies experiments better conducted early for improved parameter knowledge.
New GAN design uses conditional independence graphs to improve model-based GANs.
problem Designing model-based GANs using additional information about underlying distribution.
method Study subadditivity properties of probability divergences to design model-based GANs.
result Model-based GANs using neighborhood discriminators provide significant statistical and computational benefits.
We propose a molecular generative model based on the conditional variational autoencoder for de novo molecular design. It is specialized to control multiple molecular properties simultaneously by imposing them on a latent space. As a proof of concept, we demonstrate that it can be used to generate drug-like molecules w…
Data-driven symbol detection improves performance in complex channels.
problem Designing robust symbol detectors in systems with poorly understood channels.
method Hybrid approach combining model-based algorithms with machine learning.
result Near-optimal performance of model-based algorithms achieved without channel model knowledge.
Improved model-based reinforcement learning for multi-agent Markov games.
problem Suboptimal sample complexity for model-based algorithms in multi-agent reinforcement learning.
method Optimistic Nash Value Iteration (Nash-VI) for two-player zero-sum Markov games.
result First model-based algorithm matching information-theoretic lower bound with improved sample complexity.
Adapts MBDOE for real-time parameter estimation in complex systems.
problem Costly posterior inference and design optimization in nonlinear systems.
method Combines DAD with differentiable mechanistic models for real-time parameter estimation.
result Demonstrated on four systems, including a DC motor.
New method refines model predictions as design evolves.
problem Designing objects with desired properties using data-driven methods.
method Formalized as a game, developed autofocusing strategy for model retraining.
result Autofocusing improves model predictions in design space.
Model-based machine learning improves communication systems.
problem Improving symbol detection in communication receivers.
method Review and comparison of model-based and deep learning approaches, focusing on deep unfolding and DNN-aided hybrid algorithms.
result Different strategies of conventional deep architectures and hybrid algorithms show advantages and drawbacks.
Model-based reinforcement learning (RL) is considered to be a promising approach to reduce the sample complexity that hinders model-free RL. However, the theoretical understanding of such methods has been rather limited. This paper introduces a novel algorithmic framework for designing and analyzing model-based RL algo…
FLEX optimizes exploration for nonlinear systems with minimal data.
problem Efficient exploration of unknown nonlinear systems with limited data.
method FLEX uses optimal experimental design to maximize information gain.
result FLEX outperforms other methods in nonlinear environments and control tasks.
BRAID fine-tunes diffusion models to optimize reward models in offline scenarios.
problem Combining generative modeling and model-based optimization in offline scenarios.
method Conservative fine-tuning of diffusion models using RL to optimize reward models.
result BRAID outperforms existing methods in offline data, avoiding invalid designs.
Model-based neural networks generalize better than ReLU networks for sparse recovery.
problem Understanding and quantifying the superior generalization of model-based neural networks.
method Using complexity measures like global and local Rademacher complexities, the paper provides theoretical bounds on generalization and estimation errors.
result Model-based neural networks exhibit higher generalization capabilities for sparse recovery problems compared to ReLU networks.
New hybrid RL algorithm outperforms model-free and model-based methods.
problem Improving reinforcement learning algorithms for MDPs.
method Combines model-free and model-based learning, with a PAC analysis.
result Outperforms both model-free and model-based methods in most cases.
Designing effective model-based reinforcement learning algorithms is difficult because the ease of data generation must be weighed against the bias of model-generated data. In this paper, we study the role of model usage in policy optimization both theoretically and empirically. We first formulate and analyze a model-b…
Parameterized mathematical models play a central role in understanding and design of complex information systems. However, they often cannot take into account the intricate interactions innate to such systems. On the contrary, purely data-driven approaches do not need explicit mathematical models for data generation an…
Value functions struggle to represent transition dynamics, impacting statistical efficiency.
problem Limited representational power of value functions in capturing transition dynamics.
method Case studies of various reinforcement learning problems to explore the limitations of value-based methods.
result Value-based methods can be as efficient as model-based ones in some cases but severely underperform in others due to information loss.
Model-based reinforcement learning (MBRL) is widely seen as having the potential to be significantly more sample efficient than model-free RL. However, research in model-based RL has not been very standardized. It is fairly common for authors to experiment with self-designed environments, and there are several separate…
This work tackles model-based RL by optimizing state-action queries to learn policies with minimal data.
problem Expensive state transitions in practical RL problems limit the use of standard RL algorithms.
method Bayesian optimal experimental design to guide selection of state-action queries.
result Data-efficient RL approach that learns optimal policies with up to 1,000x less data.
Adaptive discretization improves model-based RL in large spaces.
problem Efficient model-based reinforcement learning in large state-action spaces.
method Optimistic one-step value iteration with adaptive discretization.
result Adaptive discretization leads to better performance and lower memory usage.
A new model-free subsampling method using uniform designs is proposed.
problem Model-based subsampling methods are often dependent on model assumptions.
method Developed a criterion (GEFD) and a model-free subsampling method based on uniform designs.
result The proposed method outperforms random sampling and is robust under diverse model specifications.
VMBPO optimizes model and policy jointly using variational lower-bound.
problem Data efficiency in RL with biased simulated data.
method Formulate variational objective function, use EM, iteratively improve model and policy.
result VMBPO is more sample-efficient and robust than model-free algorithms.
Reinforcement learning algorithms are gaining popularity in fields in which optimal scheduling is important, and oncology is not an exception. The complex and uncertain dynamics of cancer limit the performance of traditional model-based scheduling strategies like Optimal Control. Motivated by the recent success of mode…
Study compares data-driven vs model-based MRS quantification strategies, focusing on resilience to out-of-distribution effects.
problem Resilience to out-of-distribution effects in data-driven MRS quantification.
method Compared three data-driven strategies (supervised regression, self-supervised learning, test-time adaptation) against model-based fitting tools.
result Test-time adaptation proved most resilient to out-of-distribution effects, while self-supervised learning achieved intermediate performance.
A game-theoretic approach simplifies MBRL design and improves sample efficiency.
problem Designing stable and efficient MBRL algorithms using rich function approximators.
method Develops a game-theoretic framework where MBRL is modeled as a Stackelberg game between policy and model players.
result Proposed algorithms are highly sample efficient and match asymptotic performance of model-free policy gradient.
Insurance companies must manage millions of claims per year. While most of these claims are non-fraudulent, fraud detection is core for insurance companies. The ultimate goal is a predictive model to single out the fraudulent claims and pay out the non-fraudulent ones immediately. Modern machine learning methods are we…
MINs learn inverse mappings for high-dimensional optimization problems.
problem Data-driven optimization with high-dimensional inputs and valid subsets.
method Model Inversion Networks (MINs) learn an inverse mapping from scores to inputs.
result MINs can scale to high-dimensional input spaces and handle both offline and active data.
MOPO optimizes offline RL by penalizing dynamics uncertainty.
problem Learning policies from offline data with distributional shift.
method Modify model-based RL to avoid distributional shift.
result MOPO outperforms model-free and standard model-based RL.
Hybrid controller combines model-based and policy-based reinforcement learning.
problem Combining model-based and policy-based reinforcement learning for stability and robustness.
method Designs a hybrid controller that interpolates a model-based linear controller and a differentiable policy.
result Proven to maintain stability and universal approximation properties.
A new deep learning model improves phase retrieval performance.
problem Recovering signals from phaseless measurements.
method Hybrid model-based data-driven deep architecture (Unfolded Phase Retrieval, UPR).
result Significant improvement in phase retrieval performance.
New algorithm minimizes worst-case regret in uncertain, time-varying dynamics.
problem Model-based policy learning in uncertain, time-varying dynamics.
method Planning regret metric and iterative algorithm for minimizing it.
result Empirical evidence shows the proposed algorithm outperforms existing methods.
Models play an essential role in the design process of cyber-physical systems. They form the basis for simulation and analysis and help in identifying design problems as early as possible. However, the construction of models that comprise physical and digital behavior is challenging. Therefore, there is considerable in…
Unified framework for variable selection in model-based clustering with missing data.
problem Challenges in identifying relevant variables and handling missing data in model-based clustering.
method Unified framework incorporating a data-driven penalty matrix and a mechanism for missingness modeling.
result Achieves both asymptotic consistency and selection consistency in the presence of missing data.
Python module for RL trading in limit order books.
problem Training RL agents for algorithmic trading in limit order books.
method Model-based gym environments for reinforcement learning.
result Efficient RL training for trading problems.
Conformal Candidate Certification advances offline MBO by certifying candidate designs with statistical guarantees.
problem Offline model-based optimization
method Conformal Candidate Certification (CCC)
result CCC certifies 16.7% of an aggressive proposal pool with 0.990 empirical coverage at nominal 0.90.
This study optimizes offline reinforcement learning methods for various tasks without rewards.
problem Optimizing offline reinforcement learning for multiple tasks without rewards.
method Designing a new model-based approach with singleton absorbing MDPs to achieve optimal convergence rates.
result Achieved optimal convergence rates for offline reinforcement learning in various settings.
New method optimizes MRI sampling patterns for faster scans.
problem Accelerate MRI scans without sacrificing image quality.
method Joint learning of adaptive sampling patterns and model-based recovery.
result Improved MR image quality compared to other methods.
In this paper we propose a mixture model, SparseMix, for clustering of sparse high dimensional binary data, which connects model-based with centroid-based clustering. Every group is described by a representative and a probability distribution modeling dispersion from this representative. In contrast to classical mixtur…
Dynamic portfolio optimization is the process of sequentially allocating wealth to a collection of assets in some consecutive trading periods, based on investors' return-risk profile. Automating this process with machine learning remains a challenging problem. Here, we design a deep reinforcement learning (RL) architec…
A new clustering framework using fixed points for data analysis.
problem Lack of unified understanding and application of clustering algorithms in data analysis.
method Restated model-based clustering using fixed point theory, iteratively constructing contraction maps to find cluster centers.
result Unified clustering framework reveals convergence mechanisms and interconnections among clustering algorithms.
We study the sample complexity of model-based reinforcement learning (henceforth RL) in general contextual decision processes that require strategic exploration to find a near-optimal policy. We design new algorithms for RL with a generic model class and analyze their statistical properties. Our algorithms have sample …
VLBM learns MDP transitions from limited data, improving OPE performance.
problem Limited coverage of state and action space in offline trajectories.
method VLBM uses variational inference with RSA and branching architecture.
result VLBM outperforms existing OPE methods on deep OPE benchmark.
Novel radar waveform design for autonomous vehicles.
problem Efficient radar waveform design in time-varying environments.
method Hybrid model-driven and data-driven architecture.
result Adaptive unimodular waveform design for real-time scenarios.
New algorithms reduce regret in both stochastic and deterministic environments.
problem Designing algorithms that perform well in both types of MDPs.
method Proposed new environment norms and algorithms with variance-dependent regret bounds.
result First algorithm with simultaneously optimal bounds for both stochastic and deterministic MDPs.
Recurrent neural networks (RNNs) were designed for dealing with time-series data and have recently been used for creating predictive models from functional magnetic resonance imaging (fMRI) data. However, gathering large fMRI datasets for learning is a difficult task. Furthermore, network interpretability is unclear. T…
Study validates metrics for offline MBO using diffusion models.
problem Evaluate metrics for offline MBO without ground truth oracle.
method Propose and quantify validation metrics over datasets.
result Identify most effective validation metrics.
This work considers the sample and computational complexity of obtaining an ε-optimal policy in a discounted Markov Decision Process (MDP), given only access to a generative model. In this work, we study the effectiveness of the most natural plug-in approach to model-based planning: we build the maximum likelihood es…