arXiv research

New trade-off found in bandit problems with unknown range.

When a feed-forward neural network (FNN) is trained for source ranging in an ocean waveguide, it is difficult evaluating the range accuracy of the FNN on unlabeled test data. A fitting-based early stopping (FEAST) method is introduced to evaluate the range error of the FNN on test data where the distance of source is u…

We study the problem of learning an unknown mixture of $k$ rankings over $n$ elements, given access to noisy samples drawn from the unknown mixture. We consider a range of different noise models, including natural variants of the "heat kernel" noise framework and the Mallows model. For each of these noise models we giv…

Discrimination between non-stationarity and long-range dependency is a difficult and long-standing issue in modelling financial time series. This paper uses an adaptive spectral technique which jointly models the non-stationarity and dependency of financial time series in a non-parametric fashion assuming that the time…

Financial markets, with their vast range of different investment opportunities, can be seen as a system of many different simultaneous games with diverse and often unknown levels of risk and reward. We introduce generalizations to the classic Kelly investment game [Kelly (1956)] that incorporates these features, and us…

We consider a general statistical learning problem where an unknown fraction of the training data is corrupted. We develop a robust learning method that only requires specifying an upper bound on the corrupted data fraction. The method minimizes a risk function defined by a non-parametric distribution with unknown prob…

Proposes a new framework for open set recognition using conditional probabilistic generative models.

The paper tackles resource allocation for arms with unknown and random rewards, achieving optimal regret bounds.

New model incorporates long-range dependence in mortality rates for better valuation and risk management.

Analyzes generalization error in distributed linear regression.

CGDL improves open set recognition by learning conditional Gaussian distributions.

Identifying the unknown underlying trend of a given noisy signal is extremely useful for a wide range of applications. The number of potential trends might be exponential, which can be computationally exhaustive even for short signals. Another challenge, is the presence of abrupt changes and outliers at unknown times w…

The paper predicts responses on out-of-sample nodes using latent positions on unknown curves.

The paper develops a robust algorithm for contextual bandits with heavy-tailed rewards.

We study the minimax optimal rates for estimating a range of Integral Probability Metrics (IPMs) between two unknown probability measures, based on $n$ independent samples from them. Curiously, we show that estimating the IPM itself between probability measures, is not significantly easier than estimating the probabili…

Optimal pricing strategy for unknown valuation models with noisy feedback.

SCS identifies a range of plausible equally weighted portfolios, quantifying selection uncertainty.

The paper estimates common mean of entangled Gaussians with bounded variances.

Previous studies indicate that nonlinear properties of Gaussian time series with long-range correlations, $u_i$, can be detected and quantified by studying the correlations in the magnitude series $|u_i|$, i.e., the ``volatility''. However, the origin for this empirical observation still remains unclear, and the exact …

Blind source separation (BSS), i.e., the decoupling of unknown signals that have been mixed in an unknown way, has been a topic of great interest in the signal processing community for the last decade, covering a wide range of applications in such diverse fields as digital communications, pattern recognition, biomedica…

This paper tackles CRL for multi-node interventions, achieving identifiability guarantees.

The paper tackles data-driven optimal control of unknown nonlinear systems using RKHS.

Discovering the underlying low dimensional structure of high dimensional data has attracted a significant amount of researches recently and has shown to have a wide range of applications. As an effective dimension reduction tool, singular value decomposition is often used to analyze high dimensional matrices, which are…

Communication networks shared by many users are a widespread challenge nowadays. In this paper we address several aspects of this challenge simultaneously: learning unknown stochastic network characteristics, sharing resources with other users while keeping coordination overhead to a minimum. The proposed solution comb…

Language models are generally trained on data spanning a wide range of topics (e.g., news, reviews, fiction), but they might be applied to an a priori unknown target distribution (e.g., restaurant reviews). In this paper, we first show that training on text outside the test distribution can degrade test performance whe…

Neural networks with integer weights approximate continuous functions efficiently.

PGD algorithms solve nonlinear inverse problems with generative priors using noisy measurements.

PyChEst detects changes in non-stationary time series without distributional assumptions.

A new WNN framework selects wavelet bases for efficient learning.

We give a highly efficient "semi-agnostic" algorithm for learning univariate probability distributions that are well approximated by piecewise polynomial density functions. Let $p$ be an arbitrary distribution over an interval $I$ which is $τ$-close (in total variation distance) to an unknown probability distribution $…

New method identifies latent components in PNL mixtures without strong assumptions.

New DL approach reveals feature construction in dense samples.

Principal component analysis (PCA) is one of the most commonly used statistical procedures with a wide range of applications. Consider the points $X_1, X_2,..., X_n$ are vectors drawn i.i.d. from a distribution with mean zero and covariance $Σ$, where $Σ$ is unknown. Let $A_n = X_nX_n^T$, then $E[A_n] = Σ$. This paper …

Mix-IRLS solves imbalanced mixed linear regression problems efficiently.

The theory of Compressed Sensing (CS) asserts that an unknown signal $x\in\mathbb{R}^p$ can be accurately recovered from an underdetermined set of $n$ linear measurements with $n\ll p$, provided that $x$ is sufficiently sparse. However, in applications, the degree of sparsity $\|x\|_0$ is typically unknown, and the pro…

Given $iid$ observations from an unknown absolute continuous distribution defined on some domain $Ω$, we propose a nonparametric method to learn a piecewise constant function to approximate the underlying probability density function. Our density estimate is a piecewise constant function defined on a binary partition o…

A Bernoulli Mixture Model (BMM) is a finite mixture of random binary vectors with independent dimensions. The problem of clustering BMM data arises in a variety of real-world applications, ranging from population genetics to activity analysis in social networks. In this paper, we analyze the clusterability of BMMs from…

Optimal joint separation condition for radar and communications channels in dual-blind deconvolution.

A new algorithm for restless bandits handles long-range dependencies.

Two algorithms minimize regret in adversarial bandit problems with side-observation losses.

Domain adaptation provides a powerful set of model training techniques given domain-specific training data and supplemental data with unknown relevance. The techniques are useful when users need to develop models with data from varying sources, of varying quality, or from different time ranges. We build CrossTrainer, a…

Paper tackles transfer learning for contextual multi-armed bandits under covariate shift.

Reinforcement learning is concerned with identifying reward-maximizing behaviour policies in environments that are initially unknown. State-of-the-art reinforcement learning approaches, such as deep Q-networks, are model-free and learn to act effectively across a wide range of environments such as Atari games, but requ…

Paper proposes a shape-constrained approach to distributionally robust learning.

A main goal of regression is to derive statistical conclusions on the conditional distribution of the output variable Y given the input values x. Two of the most important characteristics of a single distribution are location and scale. Support vector machines (SVMs) are well established to estimate location functions …

This thesis explores emergent intelligence in disordered systems like spin glasses and neural networks.

Let $\mathbf{x}_j = \mathbfθ + \mathbfε_j$, $j=1,\dots,n$ be i.i.d. copies of a Gaussian random vector $\mathbf{x}\sim\mathcal{N}(\mathbfθ,\mathbfΣ)$ with unknown mean $\mathbfθ \in \mathbb{R}^d$ and unknown covariance matrix $\mathbfΣ\in \mathbb{R}^{d\times d}$. The goal of this article is to study the estimation of $…

In many applications that require matrix solutions of minimal rank, the underlying cost function is non-convex leading to an intractable, NP-hard optimization problem. Consequently, the convex nuclear norm is frequently used as a surrogate penalty term for matrix rank. The problem is that in many practical scenarios th…