arXiv research

MAPS and MAPS-SE learn from multiple suboptimal experts to improve policies efficiently.

Paper proposes a new black-box attack approach to minimize visual distortion.

PCTS optimizes noisy, delayed, multi-fidelity feedbacks in black-box optimization.

New framework converts offline to online estimation using black-box offline estimators.

Optimizes nonconvex optimization by converting it to static regret minimization.

New analysis improves black-box $k$-PCA algorithms, reducing parameter loss.

New approach tackles non-stationary multi-agent games with black-box methods.

We study the problem of generating adversarial examples in a black-box setting in which only loss-oracle access to a model is available. We introduce a framework that conceptually unifies much of the existing work on black-box attacks, and we demonstrate that the current state-of-the-art methods are optimal in a natura…

RPI combines imitation and reinforcement learning to improve policies efficiently.

Improves model classification accuracy in black-box settings.

We present a probabilistic modeling framework and adaptive sampling algorithm wherein unsupervised generative models are combined with black box predictive models to tackle the problem of input design. In input design, one is given one or more stochastic "oracle" predictive functions, each of which maps from the input …

New algorithms optimize convex functions with high-order derivatives.

We present a black-box adversarial attack algorithm which sets new state-of-the-art model evasion rates for query efficiency in the $\ell_\infty$ and $\ell_2$ metrics, where only loss-oracle access to the model is available. On two public black-box attack challenges, the algorithm achieves the highest evasion rate, sur…

Study on robustness of learning-based novelty detection methods under adversarial attacks.

How can we explain the predictions of a black-box model? In this paper, we use influence functions -- a classic technique from robust statistics -- to trace a model's prediction through the learning algorithm and back to its training data, thereby identifying training points most responsible for a given prediction. To …

A new method samples from a target density without initial samples using Monte Carlo estimation of the score.

We present a new method for design problems wherein the goal is to maximize or specify the value of one or more properties of interest. For example, in protein design, one may wish to find the protein sequence that maximizes fluorescence. We assume access to one or more, potentially black box, stochastic "oracle" predi…

This work explores adaptations of successful multi-armed bandits policies to the online contextual bandits scenario with binary rewards using binary classification algorithms such as logistic regression as black-box oracles. Some of these adaptations are achieved through bootstrapping or approximate bootstrapping, whil…

A new one-point feedback scheme improves ZO algorithms for black-box optimization.

Assessing the predictive accuracy of black box classifiers is challenging in the absence of labeled test datasets. In these scenarios we may need to rely on a human oracle to evaluate individual predictions; presenting the challenge to create query algorithms to guide the search for points that provide the most informa…

AntBO optimizes antibody design using Bayesian optimization for efficient and effective CDRH3 sequence generation.

New model-free RL algorithm tackles robust average-reward problems with finite sample complexity analysis.

A tutorial on optimizing complex functions with partial knowledge.

Study cost-effective fairness audits with partial feedback, improving over random exploration.

This paper uses NLDT to find interpretable control rules from complex DRL policies.

Deep neural network (DNN) as a popular machine learning model is found to be vulnerable to adversarial attack. This attack constructs adversarial examples by adding small perturbations to the raw input, while appearing unmodified to human eyes but will be misclassified by a well-trained classifier. In this paper, we fo…

New algorithm reduces regret bounds for Bayesian optimization with unknown hyperparameters.

Study validates metrics for offline MBO using diffusion models.

New framework for resilient bi-criteria optimization under noisy feedback.

Paper proves optimality of doubly robust estimators for treatment effects.

FPML algorithm reduces regret by limiting the number of arms chosen per round.

Model-free Reinforcement Learning (RL) algorithms such as Q-learning [Watkins, Dayan 92] have been widely used in practice and can achieve human level performance in applications such as video games [Mnih et al. 15]. Recently, equipped with the idea of optimism in the face of uncertainty, Q-learning algorithms [Jin, Al…

Oracle-efficient algorithms reduce combinatorial semi-bandit regret to logarithmic time.

New analysis shows Thompson Sampling can work with greedy approximations in combinatorial bandits.

Deep neural networks are powerful and popular learning models that achieve state-of-the-art pattern recognition performance on many computer vision, speech, and language processing tasks. However, these networks have also been shown susceptible to carefully crafted adversarial perturbations which force misclassificatio…

New algorithms sample convex bodies using Markov chains and restricted Gaussian oracles.

MAMBA learns policies competitive with multiple conflicting oracles.

We study the most practical problem setup for evaluating adversarial robustness of a machine learning system with limited access: the hard-label black-box attack setting for generating adversarial examples, where limited model queries are allowed and only the decision is provided to a queried data input. Several algori…

We study the problem of interactively learning a binary classifier using noisy labeling and pairwise comparison oracles, where the comparison oracle answers which one in the given two instances is more likely to be positive. Learning from such oracles has multiple applications where obtaining direct labels is harder bu…

New method estimates Riemannian derivatives from noisy function evaluations.

New oracle uses uncertainty for active classification with noisy feedback.

Quantum oracles help identify counterfactuals better than classical ones.

SoQal reduces oracle label requests in active learning by up to 35%.

Paper addresses online alignment of large language models under uncertain preference feedback.

We consider the problem of minimizing the sum of submodular set functions assuming minimization oracles of each summand function. Most existing approaches reformulate the problem as the convex minimization of the sum of the corresponding Lovász extensions and the squared Euclidean norm, leading to algorithms requiring …

New oracles improve stochastic optimization with noisy or biased measurements.

Algorithm solves online binary classification and infinite games using ERM oracle.

New algorithm learns efficiently with a simple 'yes/no' oracle.