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.
DFPV improves PCL for confounded bandit policy evaluation.
Our interest in this paper is in the construction of symbolic explanations for predictions made by a deep neural network. We will focus attention on deep relational machines (DRMs, first proposed by H. Lodhi). A DRM is a deep network in which the input layer consists of Boolean-valued functions (features) that are defi…
Data selection methods, such as active learning and core-set selection, are useful tools for machine learning on large datasets. However, they can be prohibitively expensive to apply in deep learning because they depend on feature representations that need to be learned. In this work, we show that we can greatly improv…
A new probabilistic approach improves deep metric learning by considering image uncertainties and class-specific variances.
A scalable method for deep metric learning using chance constraints.
Improved 3D MRI classification using contrastive learning with continuous proxy metadata.
Motivated by the need to audit complex and black box models, there has been extensive research on quantifying how data features influence model predictions. Feature influence can be direct (a direct influence on model outcomes) and indirect (model outcomes are influenced via proxy features). Feature influence can also …
Research suggests using deep learning for better recommendation systems.
New method identifies latent treatment effects from proxy models.
Neural networks improve life insurance solvency calculations.
Predictive analytics is increasingly used to guide decision-making in many applications. However, in practice, we often have limited data on the true predictive task of interest, and must instead rely on more abundant data on a closely-related proxy predictive task. For example, e-commerce platforms use abundant custom…
Cluster stability selection improves feature selection in correlated data.
We propose strategies to estimate and make inference on key features of heterogeneous effects in randomized experiments. These key features include best linear predictors of the effects using machine learning proxies, average effects sorted by impact groups, and average characteristics of most and least impacted units.…
INNs produce interval-valued uncertainty scores for DNNs.
Malicious web content is a serious problem on the Internet today. In this paper we propose a deep learning approach to detecting malevolent web pages. While past work on web content detection has relied on syntactic parsing or on emulation of HTML and Javascript to extract features, our approach operates directly on a …
Study shows latent space OOD detection isn't a reliable proxy for model performance.
Two approaches scale up DNN optimization for diverse edge devices.
Modern computer vision algorithms typically require expensive data acquisition and accurate manual labeling. In this work, we instead leverage the recent progress in computer graphics to generate fully labeled, dynamic, and photo-realistic proxy virtual worlds. We propose an efficient real-to-virtual world cloning meth…
Granger causality analysis, as one of the most popular time series causality methods, has been widely used in the economics, neuroscience. However, unobserved confounders is a fundamental problem in the observational studies, which is still not solved for the non-linear Granger causality. The application works often de…
ProxySHAP approximates Shapley and Banzhaf interactions efficiently.
A new framework improves VaR recalibration by balancing reliance on imperfect volatility proxies.
This work explores feature learning tradeoffs in neural networks.
Image classification with deep neural networks is typically restricted to images of small dimensionality such as 224 x 244 in Resnet models [24]. This limitation excludes the 4000 x 3000 dimensional images that are taken by modern smartphone cameras and smart devices. In this work, we aim to mitigate the prohibitive in…
We develop a proxy model based on deep learning methods to accelerate the simulations of oil reservoirs--by three orders of magnitude--compared to industry-strength physics-based PDE solvers. This paper describes a new architectural approach to this task, accompanied by a thorough experimental evaluation on a publicly …
Deep learning has thrived by training on large-scale datasets. However, in robotics applications sample efficiency is critical. We propose a novel adaptive masked proxies method that constructs the final segmentation layer weights from few labelled samples. It utilizes multi-resolution average pooling on base embedding…
This paper analyzes the landscape of supervised contrastive loss in over-parameterized networks.
VTD uses deep embeddings to estimate treatment effects from longitudinal data without unconfoundedness assumption.
Study accelerates NAS research with a large dataset of ZC proxies.
Unified framework for analyzing neural networks trained by gradient descent.
Study semi-supervised learning with noisy proxy covariates, deriving bounds and showing gains.
This paper aims at theoretically and empirically comparing two standard optimization criteria for Reinforcement Learning: i) maximization of the mean value and ii) minimization of the Bellman residual. For that purpose, we place ourselves in the framework of policy search algorithms, that are usually designed to maximi…
A framework uses proxies to prioritize treatment without estimating causal effects.
New method recovers latent confounders from high-dimensional proxy variables.
Single proxy variable helps estimate causal effects from confounders.
Develops methods to improve demand counterfactuals from imperfect proxies.
New method handles many noisy proxy controls for causal inference.
Predicting delayed outcomes is an important problem in recommender systems (e.g., if customers will finish reading an ebook). We formalize the problem as an adversarial, delayed online learning problem and consider how a proxy for the delayed outcome (e.g., if customers read a third of the book in 24 hours) can help mi…
We can compare the expressiveness of neural networks that use rectified linear units (ReLUs) by the number of linear regions, which reflect the number of pieces of the piecewise linear functions modeled by such networks. However, enumerating these regions is prohibitive and the known analytical bounds are identical for…
A machine learning model may exhibit discrimination when used to make decisions involving people. One potential cause for such outcomes is that the model uses a statistical proxy for a protected demographic attribute. In this paper we formulate a definition of proxy use for the setting of linear regression and present …
WTNN models survival with neural networks for maintenance data.
New conditions show proxy data can improve policy learning in sparse expert data contexts.
A faster graph kernel using optical random features.
Proposes a method to create robust linear models with noisy proxies of unobserved variables.
One of the biggest bottlenecks in a machine learning workflow is waiting for models to train. Depending on the available computing resources, it can take days to weeks to train a neural network on a large dataset with many classes such as ImageNet. For researchers experimenting with new algorithmic approaches, this is …
ESN model helps understand climate event impacts.
Bayesian method estimates causal effects with proxy networks.
Kernel methods estimate causal effects with a single proxy for deterministic confounders.
This paper presents new algorithms to solve the feature-sparsity constrained PCA problem (FSPCA), which performs feature selection and PCA simultaneously. Existing optimization methods for FSPCA require data distribution assumptions and are lack of global convergence guarantee. Though the general FSPCA problem is NP-ha…