We study the problem of off-policy policy optimization in Markov decision processes, and develop a novel off-policy policy gradient method. Prior off-policy policy gradient approaches have generally ignored the mismatch between the distribution of states visited under the behavior policy used to collect data, and what …
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,695 papers · 148 categories
Trend · papers per month
48 results for “state distribution mismatch”
Off-policy deep reinforcement learning (RL) algorithms are incapable of learning solely from batch offline data without online interactions with the environment, due to the phenomenon known as \textit{extrapolation error}. This is often due to past data available in the replay buffer that may be quite different from th…
CycleFQI tackles offline reinforcement learning for cyclic MDPs, mitigating state distribution mismatch.
problem Offline reinforcement learning for cyclic MDPs with heterogeneous dynamics and discount factors.
method CycleFQI decomposes the cyclic process into stage-wise sub-problems, using vector of stage-specific Q-functions.
result CycleFQI mitigates the curse of dimensionality and provides finite-sample suboptimality error bounds.
The paper addresses score-mismatched diffusion models and zero-shot conditional samplers.
problem Theoretical guarantees for score-mismatched diffusion models in zero-shot conditional sampling.
method Theoretical analysis of score-mismatched diffusion models and zero-shot conditional samplers.
result Theoretical performance guarantees with explicit dimensional dependencies for score-mismatched diffusion samplers.
This paper considers the classification of linear subspaces with mismatched classifiers. In particular, we assume a model where one observes signals in the presence of isotropic Gaussian noise and the distribution of the signals conditioned on a given class is Gaussian with a zero mean and a low-rank covariance matrix.…
Ensemble models improve prediction calibration for mismatched distributions.
problem Calibration issues in deep neural networks with mismatched train and test distributions.
method Simple data augmentation and mixing techniques for ensemble models.
result Improves calibration and accuracy on CIFAR10 and CIFAR100 benchmarks.
BinaryDuo: Reducing Gradient Mismatch in Binary Activation Network by Coupling Binary Activationscs.LG
BinaryDuo improves BNNs by coupling binary activations, outperforming state-of-the-art models.
problem Gradient mismatch in BNNs due to binarizing activations.
method Using gradient of smoothed loss function to estimate gradient mismatch, proposing BinaryDuo scheme with coupled ternary activations.
result BinaryDuo outperforms state-of-the-art BNNs on various benchmarks.
Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradoxstat.ML
Thompson Sampling shows polynomial regret for combinatorial semi-bandits with subgaussian rewards.
problem Finding optimal solutions in combinatorial semi-bandits with suboptimal sampling.
method Proposes Thompson Sampling with polynomial regret for linear combinatorial semi-bandits.
result Demonstrates 'mismatched sampling paradox' where knowing distributions can lead to worse performance.
New method addresses error bounds for PnP-ULA under mismatched models.
problem Error bounds for PnP-ULA under mismatched measurement and prior models.
method Posterior-L2 pseudometric to quantify error bounds.
result Explicit error bound for PnP-ULA under mismatched posterior distribution.
KalmanNet uses neural networks to improve state estimation in systems with unknown dynamics.
problem State estimation of systems with non-linear dynamics and partial information.
method KalmanNet integrates a recurrent neural network with the Kalman filter to handle non-linearities and model mismatches.
result KalmanNet outperforms classic filtering methods in systems with both mismatched and accurate domain knowledge.
New framework for RL transfer learning with state-action mismatch.
problem High sample complexity in RL from scratch.
method Embeddings to transfer knowledge between MDPs with different state- and action-spaces.
result Successful transfer learning in scenarios with state- and action-space mismatches.
Paper addresses uncertainty in model generalization under regime shifts.
problem Uncertainty in model generalization under regime changes.
method Proposes a framework to quantify and separate regime mismatch and sensitivity.
result Obtains exact decomposition and minimax lower bound for regime-aware models.
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.
We present a novel modulation level classification (MLC) method based on probability distribution distance functions. The proposed method uses modified Kuiper and Kolmogorov-Smirnov distances to achieve low computational complexity and outperforms the state of the art methods based on cumulants and goodness-of-fit test…
Current approaches for Knowledge Distillation (KD) either directly use training data or sample from the training data distribution. In this paper, we demonstrate effectiveness of 'mismatched' unlabeled stimulus to perform KD for image classification networks. For illustration, we consider scenarios where this is a comp…
Convolutional Bayesian filtering generalizes state estimation by incorporating inequality conditions.
problem Standard Bayesian filtering assumes exact conditional probabilities, limiting its applicability.
method Introducing inequality conditions transforms conditional probabilities into convolutional forms, expanding the filtering framework.
result Convolutional Bayesian filtering encompasses standard Bayesian filtering and allows for more nuanced model consideration.
Paper proposes a new framework to improve policy optimization by aligning real and simulated data distributions.
problem Inaccurate model estimation leads to performance degradation in model-based reinforcement learning.
method Introduces unsupervised model adaptation to minimize the IPM between real and simulated data distributions.
result Achieves state-of-the-art performance in sample efficiency on various continuous control tasks.
Training on mixed distributions improves test performance even when components are unrelated.
problem Improving test performance with mismatched training and test distributions.
method Analyzing mixture distributions with different training and test proportions.
result Distribution shift can be beneficial, improving test performance even when components are unrelated.
MixMOOD improves SSDL by selecting unlabelled data based on deep feature similarity.
problem Class distribution mismatch in semi-supervised learning.
method MixMOOD uses deep dataset dissimilarity measures to select unlabelled data.
result MixMOOD selects unlabelled data based on strong correlation with MixMatch accuracy.
New techniques improve distributed training with compressed gradients.
problem Gradient mismatch problem in local error feedback.
method Step-ahead error feedback and error averaging techniques.
result Our methods handle gradient mismatch and train faster than full-precision training.
New approach improves domain adaptation with label shift assumptions.
problem Improving domain adaptation when label distributions differ between source and target domains.
method Proposes generalized label shift () and modifies three DA algorithms (JAN, DANN, CDAN) to handle label distribution mismatches.
result Modified DA algorithms outperform base versions, especially with large label distribution mismatches.
Estimation of importance sampling weights for off-policy evaluation of contextual bandits often results in imbalance - a mismatch between the desired and the actual distribution of state-action pairs after weighting. In this work we present balanced off-policy evaluation (B-OPE), a generic method for estimating weights…
New state-only IL algorithm tackles MDP transition mismatch.
problem Transition dynamics mismatch between expert and imitator MDPs.
method Adversarial state-only IL with two subproblems solved iteratively.
result Effective performance improvement in transition dynamics mismatch scenarios.
The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regretcs.LG
Learning reward functions can lead to poor policy performance despite low error.
problem Low error in learned reward functions does not guarantee low regret in policy performance.
method Mathematical analysis of reward learning and policy optimization.
result A low expected test error of the reward model guarantees low worst-case regret, but error-regret mismatch can occur with certain data distributions.
The SVHN Dataset Is Deceptive for Probabilistic Generative Models Due to a Distribution Mismatchcs.CV
SVHN dataset's split affects generative models but not digit classification.
problem Distribution mismatch between SVHN training and test sets impacts generative models.
method Empirically showed distribution mismatch affects generative models; proposed mixing and re-splitting.
result Distribution mismatch in SVHN dataset significantly impacts probabilistic generative models.
A trade-off between accuracy and fairness is almost taken as a given in the existing literature on fairness in machine learning. Yet, it is not preordained that accuracy should decrease with increased fairness. Novel to this work, we examine fair classification through the lens of mismatched hypothesis testing: trying …
The performance of automatic speech recognition (ASR) systems can be significantly compromised by previously unseen conditions, which is typically due to a mismatch between training and testing distributions. In this paper, we address robustness by studying domain invariant features, such that domain information become…
New similarity measure for covariate shift improves nonparametric regression rates.
problem Improving nonparametric regression under covariate shift.
method Introducing a new similarity measure based on probability ratios.
result Shows a sharper rate of convergence compared to transfer exponent.
New algorithm solves Schrödinger bridge problem with mismatched channels.
problem Solving Schrödinger bridge problem with input and noise channel mismatch.
method Design of a Sinkhorn recursion with memory for nonlinear PDEs.
result Demonstrates solving control-affine Schrödinger bridge problem.
A contraction analysis improves model-based RL's error recovery.
problem Theoretical understanding of model-based reinforcement learning.
method Contraction analysis applied to both stochastic and deterministic state transitions.
result Error reduction in cumulative reward using branched rollouts.
Balanced Activation improves object detection performance on long-tailed datasets.
problem Mismatch between training and testing label distributions in object detection.
method Introduces Balanced Activation (Balanced Softmax and Balanced Sigmoid) to address label distribution shift.
result Balanced Activation provides ~3% gain in mAP on LVIS-1.0 compared to state-of-the-art methods.
Many sleep studies suffer from the problem of insufficient data to fully utilize deep neural networks as different labs use different recordings set ups, leading to the need of training automated algorithms on rather small databases, whereas large annotated databases are around but cannot be directly included into thes…
Stable GFlowNets prevent loss spikes and mode collapse in training.
problem Unstable training of GFlowNets leading to loss spikes and mode collapse.
method Assessed sensitivity of GFlowNet objectives, derived loss-to-TV bounds, and proposed Stable GFlowNets.
result Stable GFlowNets improve training behavior and distributional fidelity.
New algorithm reduces performance loss in IRL with mismatched transition dynamics.
problem Performance degradation in inverse reinforcement learning due to mismatched transition dynamics.
method Proposed a robust Maximum Causal Entropy (MCE) IRL algorithm leveraging robust reinforcement learning insights.
result Empirically demonstrated stable performance improvement under transition dynamics mismatches.
We study the tracking problem, namely, estimating the hidden state of an object over time, from unreliable and noisy measurements. The standard framework for the tracking problem is the generative framework, which is the basis of solutions such as the Bayesian algorithm and its approximation, the particle filters. Howe…
Conditional diffusion models can approximate target distributions well with Gaussian-mixture reverse kernels.
problem Approximating target distributions in conditional diffusion models.
method Using finite Gaussian mixtures with ReLU-network logits as reverse kernels, reducing the problem to static conditional density approximation.
result The resulting neural reverse-kernel class is dense in conditional KL divergence under exact terminal matching.
We study the estimation capacity of the generalized Lasso, i.e., least squares minimization combined with a (convex) structural constraint. While Lasso-type estimators were originally designed for noisy linear regression problems, it has recently turned out that they are in fact robust against various types of model un…
Estimating how uncertain an AI system is in its predictions is important to improve the safety of such systems. Uncertainty in predictive can result from uncertainty in model parameters, irreducible data uncertainty and uncertainty due to distributional mismatch between the test and training data distributions. Differe…
Study addresses covariate mismatch in federated learning, improving model accuracy.
problem Learning from clients with different feature sets in federated learning.
method Developed two approaches for linear prediction under covariate mismatch: plug-in estimator and impute-then-regress strategy.
result Proposed methods provide asymptotic and finite-sample learning rates, improving model accuracy.
Improving in-context learning for latent space Bayesian optimization by adapting pretraining on molecular latent space.
problem Improving in-context learning for latent space Bayesian optimization.
method Adapting pretraining on molecular latent space.
result Achieving strong performance on held-out molecular optimization benchmarks.
New model tackles real-world distribution mismatches in machine learning.
problem Real-world applications often have training and test distributions that differ.
method Developed a learning model based on information theory using importance sampling.
result The model performs better under large distribution deviations.
Study on how kernel regression models generalize to out-of-distribution data.
problem Understanding generalization in machine learning models under distributional shifts.
method Replica method from statistical physics to derive analytical formula for generalization error.
result Identified overlap matrix as key determinant of generalization performance under distribution shift.
New method improves understanding of machine learning model performance.
problem Understanding how well machine learning models generalize from training data to unseen data.
method Auxiliary Distribution Method to derive new generalization error bounds.
result Upper bounds on generalization errors are tighter and more applicable.
Subspace models play an important role in a wide range of signal processing tasks, and this paper explores how the pairwise geometry of subspaces influences the probability of misclassification. When the mismatch between the signal and the model is vanishingly small, the probability of misclassification is determined b…
We study the question of how to imitate tasks across domains with discrepancies such as embodiment, viewpoint, and dynamics mismatch. Many prior works require paired, aligned demonstrations and an additional RL step that requires environment interactions. However, paired, aligned demonstrations are seldom obtainable an…
A new method for ILO with transition model disparity using an intermediary policy.
problem Learning tasks from expert observations with different transition dynamics.
method Training an intermediary policy to match the state transitions of the expert dataset.
result Our method outperforms existing ILO approaches with transition model mismatch.
A new method for inventory control using in-context learning and generative models.
problem Inventory control with decision-dependent censoring, focusing on the censored newsvendor problem.
method In-context generative posterior sampling (ICGPS) combining modern generative models and in-context autoregressive generation.
result ICGPS achieves sublinear Bayesian regret for the censored newsvendor problem, outperforming existing methods.
Paper identifies objective mismatch in MBRL, affecting control task performance.
problem Objective mismatch in MBRL framework affects control task performance.
method Proposes re-weighting dynamics model training to mitigate mismatch.
result Likelihood of one-step ahead predictions is not always correlated with control performance.