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.
Smoothness analysis of adversarial training reveals constraints cause more non-smoothness.
Optimistic algorithm reduces regret and constraint violations in online convex optimization with adversarial constraints.
Adversarial examples are a pervasive phenomenon of machine learning models where seemingly imperceptible perturbations to the input lead to misclassifications for otherwise statistically accurate models. We propose a geometric framework, drawing on tools from the manifold reconstruction literature, to analyze the high-…
CANs improve GANs by enforcing structured constraints during training.
New algorithms control loss and constraints in uncertain, changing environments.
Optimal bounds on regret and constraint violation in adversarial COCO.
Domain knowledge helps detect adversarial examples in multi-label classification.
Memory-limited learning tackles adversarial bandits with reduced storage.
ScoreAG generates unrestricted adversarial images maintaining semantic integrity.
Generating high-quality and interpretable adversarial examples in the text domain is a much more daunting task than it is in the image domain. This is due partly to the discrete nature of text, partly to the problem of ensuring that the adversarial examples are still probable and interpretable, and partly to the proble…
Generative adversarial networks (GANs) were initially proposed to generate images by learning from a large number of samples. Recently, GANs have been used to emulate complex physical systems such as turbulent flows. However, a critical question must be answered before GANs can be considered trusted emulators for physi…
In this work we consider adversarial contextual bandits with risk constraints. At each round, nature prepares a context, a cost for each arm, and additionally a risk for each arm. The learner leverages the context to pull an arm and then receives the corresponding cost and risk associated with the pulled arm. In additi…
Paper improves COCO problem, reducing constraint violation at the cost of slightly more regret.
Adapting Hedge algorithm for semi-adversarial data with root-entropy regularization.
Graph-based framework for provably robust adversarial training.
New framework for understanding adversarial and stochastic learning.
New RL algorithm tackles adversarial RMAB with unknown transitions and bandit feedback.
New neural network smoothness constraints improve model performance.
Constraint-based learning reduces the burden of collecting labels by having users specify general properties of structured outputs, such as constraints imposed by physical laws. We propose a novel framework for simultaneously learning these constraints and using them for supervision, bypassing the difficulty of using d…
Study statistical guarantees for DRO with OT and OT-regularized divergences.
Adversarial examples are inputs to machine learning models designed to cause the model to make a mistake. They are useful for understanding the shortcomings of machine learning models, interpreting their results, and for regularisation. In NLP, however, most example generation strategies produce input text by using kno…
New algorithms improve online prediction from experts with privacy constraints.
Fair machine learning models can be vulnerable to adversarial attacks that reduce their accuracy and fairness.
Existing approaches to online convex optimization (OCO) make sequential one-slot-ahead decisions, which lead to (possibly adversarial) losses that drive subsequent decision iterates. Their performance is evaluated by the so-called regret that measures the difference of losses between the online solution and the best ye…
Unsupervised domain adaptation studies the problem of utilizing a relevant source domain with abundant labels to build predictive modeling for an unannotated target domain. Recent work observe that the popular adversarial approach of learning domain-invariant features is insufficient to achieve desirable target domain …
We study a novel multi-armed bandit problem that models the challenge faced by a company wishing to explore new strategies to maximize revenue whilst simultaneously maintaining their revenue above a fixed baseline, uniformly over time. While previous work addressed the problem under the weaker requirement of maintainin…
We present a data-driven framework for learning fair universal representations (FUR) that guarantee statistical fairness for any learning task that may not be known a priori. Our framework leverages recent advances in adversarial learning to allow a data holder to learn representations in which a set of sensitive attri…
Machine learning models, especially based on deep architectures are used in everyday applications ranging from self driving cars to medical diagnostics. It has been shown that such models are dangerously susceptible to adversarial samples, indistinguishable from real samples to human eye, adversarial samples lead to in…
New method generates diverse EHR data types while maintaining privacy.
Paper designs optimal ECOCs using IP for robust multiclass classification.
GraN-GAN normalizes gradients for better GAN performance.
New framework guides resource usage to achieve sublinear regret in adversarial settings.
Optimizes query routing to LLMs under cost and resource constraints.
Adversarial attacks on probabilistic state-space models affect latent state and policy decisions.
It has been observed that deep learning architectures tend to make erroneous decisions with high reliability for particularly designed adversarial instances. In this work, we show that the perturbation analysis of these architectures provides a framework for generating adversarial instances by convex programming which,…
There is a growing body of literature showing that deep neural networks are vulnerable to adversarial input modification. Recently this work has been extended from image classification to malware classification over boolean features. In this paper we present several new methods for training restricted networks in this …
New approach tackles resource constraints in bandit problems with weakly adaptive algorithms.
New framework enhances neural network robustness against adversarial attacks.
While progress has been made in crafting visually imperceptible adversarial examples, constructing semantically meaningful ones remains a challenge. In this paper, we propose a framework to generate semantics preserving adversarial examples. First, we present a manifold learning method to capture the semantics of the i…
The paper trains neural networks with robustness guarantees using semidefinite constraints.
Proposes a new video attack method that multiplies perturbation to improve model robustness.
Adversarial MoE learns category-specific models for product search.
Study improves privacy-preserving online prediction from experts with speed-ups.
Algorithmic trading systems are often completely automated, and deep learning is increasingly receiving attention in this domain. Nonetheless, little is known about the robustness properties of these models. We study valuation models for algorithmic trading from the perspective of adversarial machine learning. We intro…
Ideally, what confuses neural network should be confusing to humans. However, recent experiments have shown that small, imperceptible perturbations can change the network prediction. To address this gap in perception, we propose a novel approach for learning robust classifier. Our main idea is: adversarial examples for…
We suggest ways to enforce given constraints in the output of a Generative Adversarial Network (GAN) generator both for interpolation and extrapolation (prediction). For the case of dynamical systems, given a time series, we wish to train GAN generators that can be used to predict trajectories starting from a given ini…
Neural networks have been proven to be vulnerable to a variety of adversarial attacks. From a safety perspective, highly sparse adversarial attacks are particularly dangerous. On the other hand the pixelwise perturbations of sparse attacks are typically large and thus can be potentially detected. We propose a new black…
Machine learning algorithms generally suffer from a problem of explainability. Given a classification result from a model, it is typically hard to determine what caused the decision to be made, and to give an informative explanation. We explore a new method of generating counterfactual explanations, which instead of ex…