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.
R package huge simplifies graph estimation for high-dimensional data.
New algorithms reduce matching market regret to log(T) with improved stability.
New estimator stabilizes higher-order influence functions for stable statistical inference.
New estimator stabilizes higher-order influence functions for bilinear forms.
New stable HOIF estimators for statistical functionals.
Designing energy-efficient networks is of critical importance for enabling state-of-the-art deep learning in mobile and edge settings where the computation and energy budgets are highly limited. Recently, Liu et al. (2019) framed the search of efficient neural architectures into a continuous splitting process: it itera…
We propose a kernel-based nonparametric test of relative goodness of fit, where the goal is to compare two models, both of which may have unobserved latent variables, such that the marginal distribution of the observed variables is intractable. The proposed test generalizes the recently proposed kernel Stein discrepanc…
Unified framework for corruption-robust linear bandits with optimal gap-dependent misspecification bounds.
The rectified flow method is analyzed for its statistical properties.
Neural Architecture Search remains a very challenging meta-learning problem. Several recent techniques based on parameter-sharing idea have focused on reducing the NAS running time by leveraging proxy models, leading to architectures with competitive performance compared to those with hand-crafted designs. In this pape…
This work studies formal utility and privacy guarantees for a simple multiplicative database transformation, where the data are compressed by a random linear or affine transformation, reducing the number of data records substantially, while preserving the number of original input variables. We provide an analysis frame…
The paper analyzes and improves a deep learning optimization technique using matrix gradient orthogonality.
We rigorously evaluate three state-of-the-art techniques for inducing sparsity in deep neural networks on two large-scale learning tasks: Transformer trained on WMT 2014 English-to-German, and ResNet-50 trained on ImageNet. Across thousands of experiments, we demonstrate that complex techniques (Molchanov et al., 2017;…
Proposes a neural network for calibrating stochastic volatility models.
Study shows offline RL under -approximation and partial coverage is harder than previously thought.
Ultra-fast search algorithm for trillion-scale corpora with semantic flexibility.
Researchers improve tree model recovery from noisy data.
We propose a semiparametric approach, named nonparanormal skeptic, for estimating high dimensional undirected graphical models. In terms of modeling, we consider the nonparanormal family proposed by Liu et al (2009). In terms of estimation, we exploit nonparametric rank-based correlation coefficient estimators includin…
ADMM solves constrained CASH problems by breaking them into smaller, manageable pieces.
Robustifies tree learning algorithms for corrupted data.
A recent paper by Liu et al. combines the topics of adversarial training and Bayesian Neural Networks (BNN) and suggests that adversarially trained BNNs are more robust against adversarial attacks than their non-Bayesian counterparts. Here, I analyze the proposed defense and suggest that one needs to adjust the adversa…
Researchers use FIR filters to predict COVID-19 infections and recoveries.
Double Machine Learning estimators are asymptotically inadmissible under structure-agnostic models.
New method proves dimension-free convergence for ULD in KL divergence.
We consider the problem of off-policy evaluation for reinforcement learning, where the goal is to estimate the expected reward of a target policy using offline data collected by running a logging policy . Standard importance-sampling based approaches for this problem suffer from a variance that scales exponentia…
New algorithm for decentralized matching markets without prior preference rankings.
We consider the problem of training speech recognition systems without using any labeled data, under the assumption that the learner can only access to the input utterances and a phoneme language model estimated from a non-overlapping corpus. We propose a fully unsupervised learning algorithm that alternates between so…
SMI uses mixture models to improve SVGD's performance in Bayesian inference.
Two types of zeroth-order stochastic algorithms have recently been designed for nonconvex optimization respectively based on the first-order techniques SVRG and SARAH/SPIDER. This paper addresses several important issues that are still open in these methods. First, all existing SVRG-type zeroth-order algorithms suffer …
Infinite horizon off-policy policy evaluation is a highly challenging task due to the excessively large variance of typical importance sampling (IS) estimators. Recently, Liu et al. (2018a) proposed an approach that significantly reduces the variance of infinite-horizon off-policy evaluation by estimating the stationar…
Since the debut of Evolution Strategies (ES) as a tool for Reinforcement Learning by Salimans et al. 2017, there has been interest in determining the exact relationship between the Evolution Strategies gradient and the gradient of a similar class of algorithms, Finite Differences (FD).(Zhang et al. 2017, Lehman et al. …
We provide theoretical investigations into off-policy evaluation in reinforcement learning using function approximators for (marginalized) importance weights and value functions. Our contributions include: (1) A new estimator, MWL, that directly estimates importance ratios over the state-action distributions, removing …
Motivated by concerns that machine learning algorithms may introduce significant bias in classification models, developing fair classifiers has become an important problem in machine learning research. One important paradigm towards this has been providing algorithms for adversarially learning fair classifiers (Zhang e…
In this paper, we consider derivative free optimization problems, where the objective function is smooth but is computed with some amount of noise, the function evaluations are expensive and no derivative information is available. We are motivated by policy optimization problems in reinforcement learning that have rece…
Study uses machine learning and survival analysis to predict CKD progression.
We address the online linear optimization problem when the actions of the forecaster are represented by binary vectors. Our goal is to understand the magnitude of the minimax regret for the worst possible set of actions. We study the problem under three different assumptions for the feedback: full information, and the …
We propose a novel algorithm for sequential matrix completion in a recommender system setting, where the th entry of the matrix corresponds to a user 's rating of product . The objective of the algorithm is to provide a sequential policy for user-product pair recommendation which will yield the highest pos…
New curvature tensor and matrices for connection graphs derived from Bakry-Émery curvature.
In this small note we use results derived in Berestycki et al. to correct the celebrated formulae of Hagan et al. We derive explicitly the correct zero order term in the expansion of the implied volatility in time to maturity. The new term is consistent as . Furthermore, numerical simulations show that it reduc…
We present an off-policy actor-critic algorithm for Reinforcement Learning (RL) that combines ideas from gradient-free optimization via stochastic search with learned action-value function. The result is a simple procedure consisting of three steps: i) policy evaluation by estimating a parametric action-value function;…
Improved reinforcement learning for environments with distributional shifts.
As regulators pay more attentions to losses rather than gains, we are able to derive a new class of risk statistics, named regulator-based risk statistics with scenario analysis in this paper. This new class of risk statistics can be considered as a kind of risk extension of risk statistics introduced by Kou et al. \ci…
We show that the auxiliary variable method (Møller et al., 2006; Murray et al., 2006) for inference of Markov random fields can be viewed as an approximate Bayesian computation method for likelihood estimation.
Hard to estimate -accurate scores without strong assumptions.
Bayesian inference for models that have an intractable partition function is known as a doubly intractable problem, where standard Monte Carlo methods are not applicable. The past decade has seen the development of auxiliary variable Monte Carlo techniques (Møller et al., 2006; Murray et al., 2006) for tackling this pr…
In this paper, we propose a semiparametric approach, named nonparanormal skeptic, for efficiently and robustly estimating high dimensional undirected graphical models. To achieve modeling flexibility, we consider Gaussian Copula graphical models (or the nonparanormal) as proposed by Liu et al. (2009). To achieve estima…
Recent work by Jacot et al. (2018) has shown that training a neural network using gradient descent in parameter space is related to kernel gradient descent in function space with respect to the Neural Tangent Kernel (NTK). Lee et al. (2019) built on this result by establishing that the output of a neural network traine…
DAIS improves AIS by resampling, avoiding gradient issues.