New symmetries improve meta-reinforcement learning's generalization.
problem Black-box meta reinforcement learning struggles with generalization.
method Introduce symmetries to a black-box meta RL system.
result Incorporating symmetries improves generalization to new environments.
DAL enhances black-box bandit algorithms for non-stationary environments.
problem Non-stationary environments in bandit problems.
method DAL combines any stationary bandit algorithm with a change detector.
result DAL consistently outperforms state-of-the-art methods in various non-stationary scenarios.
New approach turns optimal stationary RL into non-stationary RL without prior knowledge.
problem Optimal RL in non-stationary environments without prior knowledge of non-stationarity.
method Black-box reduction of optimal stationary RL algorithms to non-stationary RL.
result Achieves optimal dynamic regret bounds in various RL settings.
Evaluation of deep reinforcement learning (RL) is inherently challenging. In particular, learned policies are largely opaque, and hypotheses about the behavior of deep RL agents are difficult to test in black-box environments. Considerable effort has gone into addressing opacity, but almost no effort has been devoted t…
Optimizing expensive black-box systems with limited data is an extremely challenging problem. As a resolution, we present a new surrogate optimization approach by addressing two gaps in prior research -- unimportant input variables and inefficient treatment of uncertainty associated with the black-box output. We first …
SyMPLER improves time series forecasting in nonstationary environments with explainable models.
problem Nonstationary time series forecasting with limited interpretability.
method Dynamic piecewise-linear approximations based on Statistical Learning Theory generalization bounds.
result SyMPLER achieves comparable performance to black-box and explainable models while maintaining interpretability.
We describe an optimal adversarial attack formulation against autoregressive time series forecast using Linear Quadratic Regulator (LQR). In this threat model, the environment evolves according to a dynamical system; an autoregressive model observes the current environment state and predicts its future values; an attac…
VOPy optimizes multiple objectives with flexible cone-based ordering.
problem Optimizing multiple objectives with partial order constraints.
method Flexible cone-based ordering, modular architecture, integration of existing and novel methods.
result Advances black-box vector optimization in noisy, discrete, or limited budget settings.
Survey of algorithms for testing AI-driven CPS safety.
problem Testing AI-driven CPS for safety in complex environments.
method Survey of applied algorithms for safety validation.
result Survey of existing tools and techniques for safety validation.
Paper proposes B3D method for black-box backdoor detection.
problem Detecting backdoor attacks in black-box models without access to training data.
method Gradient-free optimization to reverse-engineer triggers, simple strategy for reliable predictions.
result Effectiveness of B3D method corroborated on hundreds of DNN models.
Modern control theories such as systems engineering approaches try to solve nonlinear system problems by revelation of causal relationship or co-relationship among the components; most of those approaches focus on control of sophisticatedly modeled white-boxed systems. We suggest an application of actor-critic reinforc…
Bayesian method optimizes uncertain constraints in black-box function optimization.
problem Optimizing black-box functions with uncertain environmental variables.
method Distributionally robust chance-constrained Bayesian optimization.
result The method can find accurate solutions with high probability in a finite number of trials.
System interprets complex treatment effects for personalized policies.
problem Complex, hard-to-understand treatment effect models.
method Scalable, interpretable personalized experimentation system.
result Learned explanations and generated interpretable policies.
Recent advances in artificial intelligence have been driven by the presence of increasingly realistic and complex simulated environments. However, many of the existing environments provide either unrealistic visuals, inaccurate physics, low task complexity, restricted agent perspective, or a limited capacity for intera…
New approach tackles non-stationary multi-agent games with black-box methods.
problem Challenges in learning equilibria in non-stationary multi-agent systems.
method Versatile black-box approach applicable to various games, including general-sum, potential, and Markov games.
result Achieves optimal regret bounds for non-stationary games, with or without knowledge of total variation.
GACEM optimizes complex multi-modal problems using neural networks.
problem Black-box optimization and constraint satisfaction in multi-modal environments.
method Modified Cross-Entropy Method with masked auto-regressive neural network.
result GACEM outperforms traditional CEM in diverse solutions, mode discovery, and sample efficiency.
Paper proposes hybrid approach for transparent credit scoring models.
problem Lack of transparency in machine learning models limits their use in regulated environments.
method Post-hoc interpretation of black-box models guides feature selection, followed by training glass-box models.
result Reduces feature usage from 106 to 10 while maintaining comparable performance.
The Surprise index assesses autonomous systems' competency in uncertain environments.
problem Evaluating competency of autonomous systems in dynamic, uncertain environments.
method Surprise index, a measure that quantifies system performance based on available data.
result The Surprise index can be computed for dynamic systems with Gaussian marginal distributions.
DiffATD efficiently discovers targets in partially observable environments using diffusion dynamics.
problem Efficiently discovering targets in partially observable environments with limited sampling.
method DiffATD uses diffusion dynamics to maintain a belief distribution over unobserved states, balancing exploration and exploitation.
result DiffATD outperforms baselines and supervised methods in diverse domains.
Study compares high-dimensional BO algorithms on 24 functions.
problem Challenges in optimizing high-dimensional problems with BO.
method Comparison of five BO algorithms on 24 BBOB functions at varying dimensions.
result BO outperforms CMA-ES for limited evaluations, trust regions show promise.
Adaptive online learning algorithm improves history forgetting in nonstationary environments.
problem Adversarial nonstationary environments where future data can be very different from past data.
method Discounted regret in online convex optimization, FTRL-based algorithm, adaptive learning rate.
result Improves classical gradient descent with constant learning rate in online convex optimization.
Predictive models that are developed in a regulated industry or a regulated application, like determination of credit worthiness, must be interpretable and rational (e.g., meaningful improvements in basic credit behavior must result in improved credit worthiness scores). Machine Learning technologies provide very good …
We present DRLViz, a visual analytics interface to interpret the internal memory of an agent (e.g. a robot) trained using deep reinforcement learning. This memory is composed of large temporal vectors updated when the agent moves in an environment and is not trivial to understand due to the number of dimensions, depend…
Optimizes ad pruning in sponsored search systems using reinforcement learning.
problem How to efficiently select top K ads from N candidates to maximize revenue.
method Model-free reinforcement learning approach considering downstream as a black-box environment.
result Remarkable improvements in revenue achieved through reinforcement learning.
Paper tackles constrained bandit problems with a new learning framework.
problem Optimizing a black-box reward function subject to a black-box constraint function over a continuous space.
method Rectified Pessimistic-Optimistic Learning (RPOL) framework, incorporating optimistic and pessimistic GP bandit learning.
result RPOL achieves sublinear regret and minimal cumulative constraint violation.
EGL optimizes complex functions without fitting them, achieving state-of-the-art results.
problem Optimizing high-dimensional, non-convex functions in AI tasks.
method EGL trains a neural network to estimate the objective gradient directly, not fitting the function.
result EGL achieves state-of-the-art results in challenging optimization problems.
In many applications of black-box optimization, one can evaluate multiple points simultaneously, e.g. when evaluating the performances of several different neural network architectures in a parallel computing environment. In this paper, we develop a novel batch Bayesian optimization algorithm --- the parallel knowledge…
Defense strategy improves controller robustness against adversarial attacks.
problem Adversarial attacks on learning-enabled controllers in CPS.
method Two-stage defense strategy treating controller and environment as black-boxes with unknown dynamics.
result Defense strategy effectively improves controller robustness in realistic control domains.
Improves sample efficiency in RL by matching model-based gradients.
problem Lack of sample efficiency in model-free RL.
method Gradient matching between model-based and model-free RL components.
result Improves sample efficiency without increasing asymptotic bias.
Modern vision-based reinforcement learning techniques often use convolutional neural networks (CNN) as universal function approximators to choose which action to take for a given visual input. Until recently, CNNs have been treated like black-box functions, but this mindset is especially dangerous when used for control…
Machine-learning models have been recently used for detecting malicious Android applications, reporting impressive performances on benchmark datasets, even when trained only on features statically extracted from the application, such as system calls and permissions. However, recent findings have highlighted the fragili…
PWSHAP provides targeted explanations for complex models.
problem Inability of black-box models to explain targeted effects in sensitive domains.
method Augments model with DAG, uses Shapley values for causal pathway identification.
result Establishes error bounds and demonstrates resolution, interpretability, and locality.
SADCBO optimizes contextual variables by balancing relevance and cost.
problem Optimizing contextual variables with varying costs and unknown relevance.
method Adaptive selection of relevant contextual variables using sensitivity analysis and early stopping.
result Consistent improvement in optimization across various examples.
Partially observable Markov decision processes (POMDPs) are a powerful abstraction for tasks that require decision making under uncertainty, and capture a wide range of real world tasks. Today, effective planning approaches exist that generate effective strategies given black-box models of a POMDP task. Yet, an open qu…
We consider the learning of algorithmic tasks by mere observation of input-output pairs. Rather than studying this as a black-box discrete regression problem with no assumption whatsoever on the input-output mapping, we concentrate on tasks that are amenable to the principle of divide and conquer, and study what are it…
This paper considers improved forecasting in possibly nonlinear dynamic settings, with high-dimension predictors ("big data" environments). To overcome the curse of dimensionality and manage data and model complexity, we examine shrinkage estimation of a back-propagation algorithm of a deep neural net with skip-layer c…
ESS improves MCMC efficiency for correlated & multimodal distributions.
problem Slice Sampling's sensitivity to initial length scale and difficulty with correlated distributions.
method Adaptive tuning and parallel walkers for efficient sampling.
result ESS improves efficiency by more than an order of magnitude on correlated distributions.
Spanning attack improves black-box attacks with unlabeled data.
problem Query inefficiency in black-box attacks due to high input space dimensionality.
method Proposes spanning attack by constraining adversarial perturbations in a low-dimensional subspace via an auxiliary unlabeled dataset.
result Significantly improves query efficiency of black-box attacks.
Unified approach for sequence design combining likelihood-free inference and black-box optimization.
problem Designing biological sequences efficiently and accurately.
method Unified probabilistic framework integrating likelihood-free inference and black-box optimization.
result Previous optimization methods can be adapted and new algorithms proposed within this framework.
Black box machine learning models are currently being used for high stakes decision-making throughout society, causing problems throughout healthcare, criminal justice, and in other domains. People have hoped that creating methods for explaining these black box models will alleviate some of these problems, but trying t…
Machine-learning driven safety-critical autonomous systems, such as self-driving cars, must be able to detect situations where its trained model is not able to make a trustworthy prediction. Often viewed as a black-box, it is non-obvious to determine when a model will make a safe decision and when it will make an erron…
Interpretable companion model for black-box classifiers.
problem Dilemma between interpretable and black-box models.
method Trains a companion model from data and black-box model predictions, optimizing a combination of accuracy and complexity.
result Companion model provides interpretable predictions with a slight accuracy loss for user choice.
Understanding how a learned black box works is of crucial interest for the future of Machine Learning. In this paper, we pioneer the question of the global interpretability of learned black box models that assign numerical values to symbolic sequential data. To tackle that task, we propose a spectral algorithm for the …
Black-box risk scoring models permeate our lives, yet are typically proprietary or opaque. We propose Distill-and-Compare, a model distillation and comparison approach to audit such models. To gain insight into black-box models, we treat them as teachers, training transparent student models to mimic the risk scores ass…
New research shows many recent defenses against adversarial examples are ineffective against black-box attacks.
problem The robustness of recent defenses against adversarial examples is insufficient, especially against black-box attacks.
method Evaluation of nine defenses on two black-box adversarial models and six attacks on CIFAR-10 and Fashion-MNIST datasets.
result Most recent defenses provide only marginal improvements in security (<25%) compared to undefended networks. New method optimizes black-box functions using generative models and Wasserstein distance.
problem Optimizing black-box functions with stochastic responses in high dimensions.
method Deep generative surrogate models and Wasserstein distance for uncertainty estimation.
result Method outperforms state-of-the-art methods in robustness to function shape and stochasticity.
Paper proposes a new black-box attack approach to minimize visual distortion.
problem Constructing adversarial examples that minimize visual distortion in a black-box threat model.
method Learning the noise distribution of adversarial examples to approximate the gradient of a non-differentiable loss function.
result The proposed attack results in much lower visual distortion compared to state-of-the-art black-box attacks.
REST improves robustness of black-box models to geometric transformations.
problem Overconfident incorrect predictions on out-of-distribution samples.
method REinforcement Spatial Transform learner (REST) that transforms input data into in-distribution samples.
result Improves robustness to geometric transformations and sample efficiency.