Hyper addresses the hyperparameter tuning challenge in RL, improving exploration efficiency and robustness.
problem Hyperparameter tuning is a significant challenge in RL, especially for curiosity-based exploration methods.
method Hyper robustly explores by effectively regularizing exploration visits and decoupling exploitation.
result Hyper is provably efficient and robust in various RL environments.
Study explores loss design for decision trees to improve robustness against noisy labels.
problem Improving decision tree robustness to noisy labels.
method Investigated loss correction and symmetric losses, found ineffective.
result Other loss design directions need exploration for robust decision trees.
AutoBayes automates Bayesian graph exploration for robust machine learning.
problem Learning representations invariant to nuisance variations in machine learning.
method Automated Bayesian inference framework exploring different graphical models.
result Significant performance improvement with nuisance-invariant machine learning pipelines.
Paper explores robustness of CCS model for matrix completion.
problem Robustness of cross-concentrated sampling model against sparse outliers.
method Proposes Robust CUR Completion (RCURC) algorithm for efficient non-convex iterative matrix completion.
result Empirical validation of RCURC's efficiency and robustness in synthetic and real datasets.
Regularized policies are robust to adversarial rewards.
problem Understanding the effects of regularization on policy exploration and robustness.
method Using Fenchel duality to derive the dual problem of the regularized RL objective, showing the optimal policy is robust to adversarial rewards.
result Regularized policies are optimal for a reinforcement learning problem under adversarial reward conditions.
We study the problem of safe learning and exploration in sequential control problems. The goal is to safely collect data samples from operating in an environment, in order to learn to achieve a challenging control goal (e.g., an agile maneuver close to a boundary). A central challenge in this setting is how to quantify…
Robustness of deep learning models is a property that has recently gained increasing attention. We explore a notion of robustness for generative adversarial models that is pertinent to their internal interactive structure, and show that, perhaps surprisingly, the GAN in its original form is not robust. Our notion of ro…
New method uses hindsight to make exploration robust in stochastic environments.
problem Exploration in sparse-reward or reward-free environments, especially in stochastic settings.
method Learn representations of the future that capture unpredictable aspects, using them to predict and reward only the predictable parts of the world.
result Improves exploration in Atari games and Montezuma's Revenge, robust to stochasticity.
This thesis explores robust machine learning against adversarial examples.
problem How to create machine learning systems robust to adversarial examples.
method Theoretical exploration and development of new learning algorithms with robustness guarantees.
result Developed new learning algorithms with provable robustness guarantees.
Adversarial training shows promise as an approach for training models that are robust towards adversarial perturbation. In this paper, we explore some of the practical challenges of adversarial training. We present a sensitivity analysis that illustrates that the effectiveness of adversarial training hinges on the sett…
Real-world applications require RL algorithms to act safely. During learning process, it is likely that the agent executes sub-optimal actions that may lead to unsafe/poor states of the system. Exploration is particularly brittle in high-dimensional state/action space due to increased number of low-performing actions. …
A framework for robust exploration in reinforcement learning under ambiguity.
problem Optimal stopping under ambiguity in reinforcement learning.
method Continuous-time robust reinforcement learning framework using g-expectation and backward stochastic differential equations. result Constructs a robust exploratory stopping time approximating the optimal stopping time under ambiguity.
Paper explores robust regression methods and their bias-variance trade-off.
problem Understanding the trade-off between robust estimation and optimization methods.
method Examines traditional outlier-resistant robust estimation and robust optimization.
result Both methods follow converse strategies due to a bias-variance trade-off.
Improved exploration in RL with latent state marginalization.
problem Complexity of deep probabilistic models limits their practical use in reinforcement learning.
method Adopting latent variable policies within the MaxEnt framework, with low-cost marginalization of latent states.
result Effective marginalization leads to better exploration and more robust training.
Paper develops robust estimators and strategies for stochastic MABs with heavy-tailed rewards.
problem Stochastic multi-armed bandits with heavy-tailed rewards.
method Proposes a novel robust estimator and perturbation-based exploration strategy.
result Develops upper and lower regret bounds for various perturbations.
This paper explores memorization in adversarial training and proposes a mitigation algorithm.
problem Understanding and mitigating robust overfitting in adversarial training.
method Demonstrated the capacity of deep networks to memorize adversarial examples, analyzed convergence and generalization issues, and proposed a new mitigation algorithm.
result Identified robust overfitting as a significant drawback of adversarial training and proposed a mitigation algorithm.
Study finds stock and crypto markets tend to be robust, not antifragile.
problem Understanding the resilience of financial markets to noise and disorder.
method Defined and tested a measure of antifragility for complex systems, analyzed stock and crypto market returns.
result Top performers in stock and crypto markets are robust, not antifragile.
This work explores how neural network architecture affects robustness to noisy labels.
problem The impact of neural network architecture on robustness to noisy labels.
method Formal framework connecting robustness to architecture alignments, measured by predictive power in representations.
result Network robustness to noisy labels improves when its architecture is more aligned with the target function.
Robust algorithm optimizes corrupted Gaussian process bandits.
problem Sequential optimization of corrupted, expensive reward functions.
method Robust GP Phased Elimination (RGP-PE) algorithm.
result Algorithm balances robustness to corruptions with exploration and exploitation.
Optimism about the poorly understood states and actions is the main driving force of exploration for many provably-efficient reinforcement learning algorithms. We propose optimism in the face of sensible value functions (OFVF)- a novel data-driven Bayesian algorithm to constructing Plausibility sets for MDPs to explore…
We explore adversarial robustness in the setting in which it is acceptable for a classifier to abstain---that is, output no class---on adversarial examples. Adversarial examples are small perturbations of normal inputs to a classifier that cause the classifier to give incorrect output; they present security and safety …
Researchers use clustering to differentiate COVID-19 lung scans.
problem Identifying infected individuals with COVID-19.
method Applied unsupervised clustering techniques using PCA, K-Means++, and RCC.
result KM++ and RCC algorithms improved in clustering COVID-19 lung scans.
DR-RPO optimizes robust policies in RL with limited interaction, achieving sublinear regret.
problem Policy optimization in RL under distribution shift and adversarial dynamics.
method DR-RPO algorithm incorporating reference-policy regularization and upper confidence bonus for exploration.
result DR-RPO achieves sublinear regret and polynomial suboptimality bounds in robust RL.
This paper concerns the problem of learning control policies for an unknown linear dynamical system to minimize a quadratic cost function. We present a method, based on convex optimization, that accomplishes this task robustly: i.e., we minimize the worst-case cost, accounting for system uncertainty given the observed …
Improved Thompson Sampling for Bayesian Optimization.
problem Handling the exploitation-exploration dilemma in Bayesian optimization.
method Incorporating epsilon-greedy policy into Thompson Sampling.
result Epsilon-greedy Thompson Sampling outperforms standard TS extremes.
Self-supervision improves GCNs' generalizability and robustness.
problem Improving graph convolutional networks' performance.
method Three mechanisms of self-supervision, multi-task learning, and graph adversarial training.
result Self-supervision enhances GCNs' robustness and generalizability.
AlphaSAGE mines diverse alphas via GFlowNets, overcoming RL issues.
problem Reward sparsity, inadequate sequential representations, and single optimal mode issues in RL for alphas.
method Structure-aware encoder (RGCN), GFlowNets, dense reward structure.
result Empirically outperforms existing baselines in mining diverse alphas.
MOOSE improves offline RL robustness by using dynamics models.
problem Low robustness of model-free offline RL algorithms in industrial settings.
method MOOSE uses dynamics models to assess policy performance, keeping policies within data support.
result MOOSE outperforms state-of-the-art model-free offline RL algorithms in robust performance.
This paper investigates the effectiveness of adversarial training in enhancing the robustness of Deep Q-Network (DQN) policies to state-space perturbations. We first present a formal analysis of adversarial training in DQN agents and its performance with respect to the proportion of adversarial perturbations to nominal…
Study shows how to manipulate VAEs for attacks and assess their robustness.
problem Adversarial attacks on Variational Autoencoders (VAE).
method Examine modifications to VAEs and propose metrics for robustness.
result Metrics to quantify the robustness of VAEs to adversarial attacks.
Exploring Sasaki metrics in joined manifolds.
problem Existence of constant scalar curvature Sasaki metrics in joined manifolds.
method Investigating the Sasaki cone of joined manifolds and considering continuous families of extremal Sasaki twins.
result Conditions for the existence of constant scalar curvature Sasaki metrics in joined manifolds.
Deep Neural Network has proved its potential in various perception tasks and hence become an appealing option for interpretation and data processing in security sensitive systems. However, security-sensitive systems demand not only high perception performance, but also design robustness under various circumstances. Unl…
Our work is a simple extension of the paper "Exploration by Random Network Distillation". More in detail, we show how to efficiently combine Intrinsic Rewards with Experience Replay in order to achieve more efficient and robust exploration (with respect to PPO/RND) and consequently better results in terms of agent perf…
The study of adversarial robustness has so far largely focused on perturbations bound in p-norms. However, state-of-the-art models turn out to be also vulnerable to other, more natural classes of perturbations such as translations and rotations. In this work, we thoroughly investigate the vulnerability of neural networ…
A reinforcement learning agent tries to maximize its cumulative payoff by interacting in an unknown environment. It is important for the agent to explore suboptimal actions as well as to pick actions with highest known rewards. Yet, in sensitive domains, collecting more data with exploration is not always possible, but…
New methods solve sparse estimation robustly, even with outliers.
problem Sparse estimation in high-dimensional data with outliers.
method Non-convex optimization formulations for robust sparse mean estimation and PCA.
result Any approximate stationary point yields near-optimal solutions.
The paper assesses machine learning robustness with covariate perturbations.
problem Ensuring robustness of machine learning models against adversarial attacks and data changes.
method Proposes a framework using covariate perturbation techniques to assess model robustness.
result Demonstrates the effectiveness of the approach in comparing robustness across models and identifying instabilities.
New Muon and Momo variants improve neural network optimization robustness.
problem Improving neural network optimization methods.
method Systematic exploration of non-Euclidean gradient descent variants.
result Momo variants of Muon are more robust to hyperparameter tuning.
New method improves GP uncertainty quantification for misspecified priors.
problem Uncertainty quantification for GPs under incorrect priors.
method Constructs a confidence sequence using martingale techniques.
result Empirically outperforms standard GP methods in robustness and utility for Bayesian Optimization.
Efficient exploration is necessary to achieve good sample efficiency for reinforcement learning in general. From small, tabular settings such as gridworlds to large, continuous and sparse reward settings such as robotic object manipulation tasks, exploration through adding an uncertainty bonus to the reward function ha…
Adaptive networks improve model robustness through conditional normalization.
problem Limited robustness of adversarial-trained networks due to network capacity and training samples.
method Proposes a conditional normalization module to adapt networks during adversarial training.
result Adaptive networks outperform both clean validation accuracy and robustness compared to non-adaptive counterparts.
In this paper we propose a novel augmentation technique that improves not only the performance of deep neural networks on clean test data, but also significantly increases their robustness to random transformations, both affine and projective. Inspired by ManiFool, the augmentation is performed by a line-search manifol…
Robust Markov Decision Processes (RMDPs) intend to ensure robustness with respect to changing or adversarial system behavior. In this framework, transitions are modeled as arbitrary elements of a known and properly structured uncertainty set and a robust optimal policy can be derived under the worst-case scenario. In t…
Paper explores robust estimators for kernel exponential families using smoothed total variation distances.
problem Outliers can severely impact classical estimators in statistical inference.
method Proposes smoothed total variation (STV) distance as a class of IPMs for robust estimation of kernel exponential families.
result STV-based estimators are robust against distribution contamination for kernel exponential families.
The paper explores robustness in linear regression models under adversarial attacks.
problem The impact of test-time adversarial attacks on linear regression models.
method Quantitative estimates and phase transitions analysis.
result Precise characterization of tradeoffs between adversarial robustness and accuracy.
RECODE uses clustering and embedding to track state visitation counts in RL.
problem Efficient novelty-based exploration in nonstationary RL environments.
method Non-parametric clustering, online density estimation, inverse dynamics loss.
result RECODE achieves state-of-the-art performance in challenging RL tasks.
The importance of training robust neural network grows as 3D data is increasingly utilized in deep learning for vision tasks in robotics, drone control, and autonomous driving. One commonly used 3D data type is 3D point clouds, which describe shape information. We examine the problem of creating robust models from the …
New AIM algorithm optimizes exploration-exploitation in bandits.
problem Balancing exploration and exploitation in decision-making.
method Approximate Information Maximization (AIM) algorithm.
result AIM outperforms Infomax and Thompson sampling with enhanced speed and tractability.