arXiv research

Optimistic RL algorithms are simplified for deep RL with competitive performance.

DARLING tackles non-stationary RL with guarantees, improving dynamic regret.

This work extends ME-RL using diffusion models to sample optimal policies.

We reformulate the option framework as two parallel augmented MDPs. Under this novel formulation, all policy optimization algorithms can be used off the shelf to learn intra-option policies, option termination conditions, and a master policy over options. We apply an actor-critic algorithm on each augmented MDP, yieldi…

Consider a Markov decision process (MDP) that admits a set of state-action features, which can linearly express the process's probabilistic transition model. We propose a parametric Q-learning algorithm that finds an approximate-optimal policy using a sample size proportional to the feature dimension $K$ and invariant …

PiNGDA learns beneficial noise for graph augmentation stability.

We introduce the active exploration problem in Markov decision processes (MDPs). Each state of the MDP is characterized by a random value and the learner should gather samples to estimate the mean value of each state as accurately as possible. Similarly to active exploration in multi-armed bandit (MAB), states may have…

Active Reinforcement Learning (ARL) is a twist on RL where the agent observes reward information only if it pays a cost. This subtle change makes exploration substantially more challenging. Powerful principles in RL like optimism, Thompson sampling, and random exploration do not help with ARL. We relate ARL in tabular …

Bayesian regularization improves policy performance in noisy MDPs.

SapAugment learns adaptive augmentation policies for better model training.

PANDA augments data to regularize GLM estimation and inference.

Enhanced financial forecasting using supervised autoencoders with noise augmentation and triple labeling.

New algorithm reduces regret for linear bandits with unknown noise variance.

We propose an AdaPtive Noise Augmentation (PANDA) technique to regularize the estimation and construction of undirected graphical models. PANDA iteratively optimizes the objective function given the noise augmented data until convergence to achieve regularization on model parameters. The augmented noises can be designe…

MetaCURL tackles non-stationary MDPs with optimal dynamic regret.

Dropout is typically interpreted as bagging a large number of models sharing parameters. We show that using dropout in a network can also be interpreted as a kind of data augmentation in the input space without domain knowledge. We present an approach to projecting the dropout noise within a network back into the input…

Theoretical framework for data augmentation in finance improves portfolio construction.

Optimal strategy for reinforcement learning with delayed observations.

The ability to detect sparse signals from noisy high-dimensional data is a top priority in modern science and engineering. A sparse solution of the linear system $A ρ= b_0$ can be found efficiently with an $l_1$-norm minimization approach if the data is noiseless. Detection of the signal's support from data corrupted b…

There is broad interest in creating RL agents that can solve many (related) tasks and adapt to new tasks and environments after initial training. Model-based RL leverages learned surrogate models that describe dynamics and rewards of individual tasks, such that planning in a good surrogate can lead to good control of t…

Deploying machine learning systems in the real world requires both high accuracy on clean data and robustness to naturally occurring corruptions. While architectural advances have led to improved accuracy, building robust models remains challenging. Prior work has argued that there is an inherent trade-off between robu…

New algorithm reduces reinforcement learning regret for linear MDPs with unknown transitions.

The paper examines how adversarial training and noise affect neural network performance.

CutMix enhances feature learning in neural networks, improving test accuracy.

Diffusion models optimize objectives similar to ELBO with Gaussian noise augmentation.

In order to satisfy safety conditions, an agent may be constrained from acting freely. A safe controller can be designed a priori if an environment is well understood, but not when learning is employed. In particular, reinforcement learned (RL) controllers require exploration, which can be hazardous in safety critical …

Large datasets often have unreliable labels-such as those obtained from Amazon's Mechanical Turk or social media platforms-and classifiers trained on mislabeled datasets often exhibit poor performance. We present a simple, effective technique for accounting for label noise when training deep neural networks. We augment…

Introduces data augmentation for graph convolutional networks, proposing Monte Carlo Graph Learning.

AugBagg improves random forest accuracy with added noise variables.

Humans achieve efficient learning by relying on prior knowledge about the structure of naturally occurring tasks. There is considerable interest in designing reinforcement learning (RL) algorithms with similar properties. This includes proposals to learn the learning algorithm itself, an idea also known as meta learnin…

NA$_0$CT$^2$ improves tensor regression predictions with $\ell_0$ regularization.

Researchers use human-in-the-loop to create counterfactually augmented data, improving model performance.

Paper tackles robust MDPs with sample complexity guarantees.

The paper tackles efficient exploration in MDPs to learn accurate models.

NAPP-ERM improves ERM with differential privacy guarantees by iteratively achieving target regularization and delivering strong convexity.

DACL tackles domain-specific contrastive learning by using Mixup noise.

AugLoss combines data augmentation and robust loss functions for robust DL models.

Study examines how data augmentation impacts optimization in linear regression.

Real-time speech enhancement model removes various noises and reverb.

The paper reveals that baselines significantly impact RL algorithms' convergence.

MVPI framework optimizes risk in reinforcement learning, improving performance in robot simulations.

Transfer learning and data augmentation improve stock classification performance.

Novel bio-inspired masking for robust speech emotion recognition.

We develop model free PAC performance guarantees for multiple concurrent MDPs, extending recent works where a single learner interacts with multiple non-interacting agents in a noise free environment. Our framework allows noisy and resource limited communication between agents, and develops novel PAC guarantees in this…

This paper explores the use of adversarial examples in training speech recognition systems to increase robustness of deep neural network acoustic models. During training, the fast gradient sign method is used to generate adversarial examples augmenting the original training data. Different from conventional data augmen…

Semi-supervised learning lately has shown much promise in improving deep learning models when labeled data is scarce. Common among recent approaches is the use of consistency training on a large amount of unlabeled data to constrain model predictions to be invariant to input noise. In this work, we present a new perspe…

The paper provides theoretical guarantees for behavior cloning using generative models.

New RL algorithm for linear MDPs with nearly optimal regret.