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.
Detects unusual inputs to neural networks to prevent flawed predictions.
Safety evaluation of self-driving technologies has been extensively studied. One recent approach uses Monte Carlo based evaluation to estimate the occurrence probabilities of safety-critical events as safety measures. These Monte Carlo samples are generated from stochastic input models constructed based on real-world d…
Bayesian approach quantifies uncertainty in LLM evaluations.
Robust OPE framework uses human inputs to improve policy evaluation in changing environments.
We analyze the adversarial examples problem in terms of a model's fault tolerance with respect to its input. Whereas previous work focuses on arbitrarily strict threat models, i.e., -perturbations, we consider arbitrary valid inputs and propose an information-based characteristic for evaluating tolerance to diverse …
VAIOM models financial returns using continuous input and categorical output.
New saliency evaluations focus on completeness and soundness, improving explanations.
We consider the problem of robust optimization within the well-established Bayesian optimization (BO) framework. While BO is intrinsically robust to noisy evaluations of the objective function, standard approaches do not consider the case of uncertainty about the input parameters. In this paper, we propose Noisy-Input …
Bayesian Optimization (BO) methods are useful for optimizing functions that are expen- sive to evaluate, lack an analytical expression and whose evaluations can be contaminated by noise. These methods rely on a probabilistic model of the objective function, typically a Gaussian process (GP), upon which an acquisition f…
When using Convolutional Neural Networks (CNNs) for segmentation of organs and lesions in medical images, the conventional approach is to work with inputs and outputs either as single slice (2D) or whole volumes (3D). One common alternative, in this study denoted as pseudo-3D, is to use a stack of adjacent slices as in…
Bayesian optimization (BO) methods are useful for optimizing functions that are expensive to evaluate, lack an analytical expression and whose evaluations can be contaminated by noise. These methods rely on a probabilistic model of the objective function, typically a Gaussian process (GP), upon which an acquisition fun…
Interpretability is an important area of research for safe deployment of machine learning systems. One particular type of interpretability method attributes model decisions to input features. Despite active development, quantitative evaluation of feature attribution methods remains difficult due to the lack of ground t…
Bayesian optimisation (BO) has been a successful approach to optimise functions which are expensive to evaluate and whose observations are noisy. Classical BO algorithms, however, do not account for errors about the location where observations are taken, which is a common issue in problems with physical components. In …
This paper evaluates various representations for robotics tasks, improving performance in lifting, stacking, and pushing.
A common data mining task on networks is community detection, which seeks an unsupervised decomposition of a network into structural groups based on statistical regularities in the network's connectivity. Although many methods exist, the No Free Lunch theorem for community detection implies that each makes some kind of…
Fairness is a critical trait in decision making. As machine-learning models are increasingly being used in sensitive application domains (e.g. education and employment) for decision making, it is crucial that the decisions computed by such models are free of unintended bias. But how can we automatically validate the fa…
Optimizes function networks by selectively evaluating parts of the network, reducing costs.
Embeddings leak sensitive information about input data, which can be recovered or inferred.
Accelerates Bayesian optimization of function networks with partial evaluations.
Study tests if input gradients highlight discriminative features, finds they often fail.
The problem of attributing a deep network's prediction to its \emph{input/base} features is well-studied. We introduce the notion of \emph{conductance} to extend the notion of attribution to the understanding the importance of \emph{hidden} units. Informally, the conductance of a hidden unit of a deep network is the \e…
The Neural Testbed evaluates joint predictions of neural agents, revealing their limitations.
Bayesian optimization is a powerful tool for expensive stochastic black-box optimization problems such as simulation-based optimization or machine learning hyperparameter tuning. Many stochastic objective functions implicitly require a random number seed as input. By explicitly reusing a seed a user can exploit common …
Proposes a new method to selectively access privileged information in reinforcement learning.
A new framework evaluates model performance on single input points, revealing insights into data and model structure.
IA-BMA adapts model weights to inputs for better predictions.
LLMs' explanations are often insufficient and vary with input distribution.
New method distinguishes predictive distribution estimators in high-dimensional inputs.
Humans increasingly interact with Artificial intelligence(AI) systems. AI systems are optimized for objectives such as minimum computation or minimum error rate in recognizing and interpreting inputs from humans. In contrast, inputs created by humans are often treated as a given. We investigate how inputs of humans can…
New method evaluates visual explanations of deep models using adversarial perturbations.
AIRBO optimizes robustly under uncertain inputs.
Paper introduces Modular Jets for diagnosing model decompositions in pipelines.
ProEval efficiently estimates AI performance and discovers failures using pre-trained Gaussian Processes.
In this work, we aim to solve data-driven optimization problems, where the goal is to find an input that maximizes an unknown score function given access to a dataset of inputs with corresponding scores. When the inputs are high-dimensional and valid inputs constitute a small subset of this space (e.g., valid protein s…
New method improves interpretability of fMRI decoding models.
We introduce a two-player contest for evaluating the safety and robustness of machine learning systems, with a large prize pool. Unlike most prior work in ML robustness, which studies norm-constrained adversaries, we shift our focus to unconstrained adversaries. Defenders submit machine learning models, and try to achi…
Neural networks are vulnerable to small adversarial perturbations. Existing literature largely focused on understanding and mitigating the vulnerability of learned models. In this paper, we demonstrate an intriguing phenomenon about the most popular robust training method in the literature, adversarial training: Advers…
VB-Score evaluates AI systems without ground truth, revealing robustness.
Extensions to given-data Sobol' index estimators for large models.
This research evaluates learning models for bionic robots, focusing on transfer function identification.
This paper develops a framework for training and evaluating neural networks for MPC.
Deployment of deep neural networks (DNNs) in safety- or security-critical systems requires provable guarantees on their correct behaviour. A common requirement is robustness to adversarial perturbations in a neighbourhood around an input. In this paper we focus on the norm and aim to compute, for a trained DNN an…
State-of-the-art deep neural networks (DNNs) are highly effective in solving many complex real-world problems. However, these models are vulnerable to adversarial perturbation attacks, and despite the plethora of research in this domain, to this day, adversaries still have the upper hand in the cat and mouse game of ad…
Proposes a method to handle missing inputs in Bayesian optimization.
We present a deep neural network-based methodology for synthesising percussive sounds with control over high-level timbral characteristics of the sounds. This approach allows for intuitive control of a synthesizer, enabling the user to shape sounds without extensive knowledge of signal processing. We use a feedforward …
New algorithm adds Hessian regularization to improve neural network robustness.
When simulating a complex stochastic system, the behavior of output response depends on input parameters estimated from finite real-world data, and the finiteness of data brings input uncertainty into the system. The quantification of the impact of input uncertainty on output response has been extensively studied. Most…
Safe active learning for time-series models with Gaussian processes.