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.
Develops significance tests for neural networks without strong assumptions or excessive computation.
Paper proposes a black-box technique to generate adversarial samples.
Black-box optimization is primarily important for many compute-intensive applications, including reinforcement learning (RL), robot control, etc. This paper presents a novel theoretical framework for black-box optimization, in which our method performs stochastic update with the implicit natural gradient of an exponent…
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 approach tackles non-stationary multi-agent games with black-box methods.
Faced with distribution shift between training and test set, we wish to detect and quantify the shift, and to correct our classifiers without test set labels. Motivated by medical diagnosis, where diseases (targets) cause symptoms (observations), we focus on label shift, where the label marginal changes but the …
Deep-PrAE improves rare-event simulation for black-box systems.
New method optimizes black-box functions using generative models and Wasserstein distance.
Survey of algorithms for testing AI-driven CPS safety.
In science and medicine, model interpretations may be reported as discoveries of natural phenomena or used to guide patient treatments. In such high-stakes tasks, false discoveries may lead investigators astray. These applications would therefore benefit from control over the finite-sample error rate of interpretations…
Powerful adversarial attack methods are vital for understanding how to construct robust deep neural networks (DNNs) and for thoroughly testing defense techniques. In this paper, we propose a black-box adversarial attack algorithm that can defeat both vanilla DNNs and those generated by various defense techniques develo…
Method optimizes diffusion model generation to meet user preferences.
The paper tests semantic importance in opaque models using betting.
Interpretable machine learning has become a strong competitor for traditional black-box models. However, the possible loss of the predictive performance for gaining interpretability is often inevitable, putting practitioners in a dilemma of choosing between high accuracy (black-box models) and interpretability (interpr…
While autonomous vehicle (AV) technology has shown substantial progress, we still lack tools for rigorous and scalable testing. Real-world testing, the evaluation method, is dangerous to the public. Moreover, due to the rare nature of failures, billions of miles of driving are needed to statisticall…
Develops a method to continuously audit black-box conditional quantile forecasts.
In recent years, deep neural networks (DNN) have become a highly active area of research, and shown remarkable achievements on a variety of computer vision tasks. DNNs, however, are known to often make overconfident yet incorrect predictions on out-of-distribution samples, which can be a major obstacle to real-world de…
New framework limits testing algorithmic stability under computational constraints.
Hybrid neural network infers states from black-box systems.
Analyzing large-scale, multi-experiment studies requires scientists to test each experimental outcome for statistical significance and then assess the results as a whole. We present Black Box FDR (BB-FDR), an empirical-Bayes method for analyzing multi-experiment studies when many covariates are gathered per experiment.…
AST provides a method to validate safe autonomy without unsafe simplifications.
Develops causal explanations for black-box classifiers.
Real-world machine learning applications often have complex test metrics, and may have training and test data that are not identically distributed. Motivated by known connections between complex test metrics and cost-weighted learning, we propose addressing these issues by using a weighted loss function with a standard…
Model proposes how regulators should oversee complex algorithms in high-stakes applications.
Trieste optimizes black-box functions using TensorFlow for efficient decision-making.
This paper explores how the generalization of substitute classifiers affects the success of black-box adversarial attacks.
Proposes a method to ensure accurate estimation of rare events in AI systems.
The paper proposes a test to assess rater accuracy while accounting for rater covariates.
New algorithm tests model calibration in nearly-linear time.
Research in both machine learning and psychology suggests that salient examples can help humans to interpret learning models. To this end, we take a novel look at black box interpretation of test predictions in terms of training examples. Our goal is to ask `which training examples are most responsible for a given set …
With the rapid adoption of machine learning systems in sensitive applications, there is an increasing need to make black-box models explainable. Often we want to identify an influential group of training samples in a particular test prediction for a given machine learning model. Existing influence functions tackle this…
MPHD transfers knowledge across different domains for Bayesian optimization.
New method estimates data influence efficiently by leveraging test samples.
Recently, neural networks trained as optimizers under the "learning to learn" or meta-learning framework have been shown to be effective for a broad range of optimization tasks including derivative-free black-box function optimization. Recurrent neural networks (RNNs) trained to optimize a diverse set of synthetic non-…
Most of the work on interpretable machine learning has focused on designing either inherently interpretable models, which typically trade-off accuracy for interpretability, or post-hoc explanation systems, which lack guarantees about their explanation quality. We propose an alternative to these approaches by directly r…
Deep neural networks (DNNs) are known for their vulnerability to adversarial examples. These are examples that have undergone small, carefully crafted perturbations, and which can easily fool a DNN into making misclassifications at test time. Thus far, the field of adversarial research has mainly focused on image model…
S-LIME stabilizes LIME for more reliable model explanations.
New framework for variational coresets simplifies Bayesian inference for complex models.
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 …
Proposes a black-box attack to test clustering algorithms' robustness.
Sparse perturbations improve convergence in SZO methods for faster training.
NeurT-FDR controls FDR by incorporating auxiliary covariates in deep learning.
Throughout the last decade, random forests have established themselves as among the most accurate and popular supervised learning methods. While their black-box nature has made their mathematical analysis difficult, recent work has established important statistical properties like consistency and asymptotic normality b…
PyBADS optimizes complex functions quickly and reliably.
Framework certifies fairness of machine learning models interactively and privately.
Survey and benchmark high-dimensional Bayesian optimization of discrete sequences.
GTBO uses group testing to optimize high-dimensional functions efficiently.
Improved A/B testing by leveraging system similarities.