arXiv research

New method for fair resource allocation in AI-aware networks with unknown utility functions.

New algorithm tackles unknown utility network resource allocation.

Assessing the predictive accuracy of black box classifiers is challenging in the absence of labeled test datasets. In these scenarios we may need to rely on a human oracle to evaluate individual predictions; presenting the challenge to create query algorithms to guide the search for points that provide the most informa…

New approach for learning with unknown utilities without explicit specification.

Paper solves investment and consumption problem with unknown risk, providing explicit solutions.

The study bounds the utility of empirically optimal portfolios using stock return data.

Enforcing safety is a key aspect of many problems pertaining to sequential decision making under uncertainty, which require the decisions made at every step to be both informative of the optimal decision and also safe. For example, we value both efficacy and comfort in medical therapy, and efficiency and safety in robo…

Investor maximizes utility from an unknown claim using robust optimization.

This paper considers portfolio construction in a dynamic setting. We specify a loss function comprised of utility and complexity components with an unknown tradeoff parameter. We develop a novel regret-based criterion for selecting the tradeoff parameter to construct optimal sparse portfolios over time.

Modeling driver trajectories using inverse reinforcement learning and random utility.

One of the key challenges in applying reinforcement learning to real-life problems is that the amount of train-and-error required to learn a good policy increases drastically as the task becomes complex. One potential solution to this problem is to combine reinforcement learning with automated symbol planning and utili…

Optimistic Thompson Sampling reduces regret in unknown multi-player games.

Paper tackles open set domain adaptation by detecting unknown classes.

Algorithm improves RL model selection for repeated games with utility maximization.

We consider the problem of learning by demonstration from agents acting in unknown stochastic Markov environments or games. Our aim is to estimate agent preferences in order to construct improved policies for the same task that the agents are trying to solve. To do so, we extend previous probabilistic approaches for in…

We consider the problem of learning by demonstration from agents acting in unknown stochastic Markov environments or games. Our aim is to estimate agent preferences in order to construct improved policies for the same task that the agents are trying to solve. To do so, we extend previous probabilistic approaches for in…

New algorithm recovers matrices with unknown correspondences.

Method learns dynamics of slow variables from stochastic data.

MAGI-X learns unknown dynamics from data without numerical integration.

A new method learns the optimal pricing map for semiparametric dynamic pricing problems.

Proposes RPG-RT for red-teaming T2I models without internal access.

Paper proposes new strategies for better portfolio estimation in long-term investments with unknown distributions.

We study pool-based active learning with abstention feedbacks where a labeler can abstain from labeling a queried example with some unknown abstention rate. This is an important problem with many useful applications. We take a Bayesian approach to the problem and develop two new greedy algorithms that learn both the cl…

The implementation of smart building technology in the form of smart infrastructure applications has great potential to improve sustainability and energy efficiency by leveraging humans-in-the-loop strategy. However, human preference in regard to living conditions is usually unknown and heterogeneous in its manifestati…

Algorithm selects optimal experiments in Markov chains to learn unknown quantities.

In the paper, we consider three quadratic optimization problems which are frequently applied in portfolio theory, i.e, the Markowitz mean-variance problem as well as the problems based on the mean-variance utility function and the quadratic utility.Conditions are derived under which the solutions of these three optimiz…

We study pool-based active learning with abstention feedbacks, where a labeler can abstain from labeling a queried example with some unknown abstention rate. This is an important problem with many useful applications. We take a Bayesian approach to the problem and develop two new greedy algorithms that learn both the c…

We propose the Autoencoding Binary Classifiers (ABC), a novel supervised anomaly detector based on the Autoencoder (AE). There are two main approaches in anomaly detection: supervised and unsupervised. The supervised approach accurately detects the known anomalies included in training data, but it cannot detect the unk…

GMVAE improves open-set classification by clustering latent representations.

We study a coupled system of controlled stochastic differential equations (SDEs) driven by a Brownian motion and a compensated Poisson random measure, consisting of a forward SDE in the unknown process $X(t)$ and a \emph{predictive mean-field} backward SDE (BSDE) in the unknowns $Y(t), Z(t), K(t,\cdot)$. The driver of …

Inpatient care is a large share of total health care spending, making analysis of inpatient utilization patterns an important part of understanding what drives health care spending growth. Common features of inpatient utilization measures include zero inflation, over-dispersion, and skewness, all of which complicate st…

This paper solves robust utility maximization with unknown claim dependencies.

Optimizes investment and reinsurance strategies with unknown parameters.

This research generates synthetic data streams for handling concept drifts and novel classes.

We propose a sampling scheme suitable for reducing a data set prior to selecting a hypothesis with minimum empirical risk. The sampling only considers a subset of the ultimate (unknown) hypothesis set, but can nonetheless guarantee that the final excess risk will compare favorably with utilizing the entire original dat…

Predicting absolute magnitude of fluctuations of price, even if their sign remains unknown, is important for risk analysis and for option prices. In the present work, we display our predictions about absolute magnitude of daily fluctuations of the Dow Jones Industrials Average (DJIA), utilizing the original theory of c…

Paper relaxes differential privacy for correlated features, improving privacy-utility trade-off.

Nonparametric adaptive robust control tackles model uncertainty in stochastic processes.

This paper concerns the problem of recovering an unknown but structured signal $x \in R^n$ from $m$ quadratic measurements of the form $y_r=|<a_r,x>|^2$ for $r=1,2,...,m$. We focus on the under-determined setting where the number of measurements is significantly smaller than the dimension of the signal ($m<<n$). We for…

Guaranteed reachable set for unknown nonlinear systems on manifolds.

Many complex dynamical phenomena can be effectively modeled by a system that switches among a set of conditionally linear dynamical modes. We consider two such models: the switching linear dynamical system (SLDS) and the switching vector autoregressive (VAR) process. Our Bayesian nonparametric approach utilizes a hiera…

The paper models and predicts co-occurrence counts using Gamma regression.

Expands Bayesian experiment design framework to account for model discrepancies.

Model-based reinforcement learning algorithms make decisions by building and utilizing a model of the environment. However, none of the existing algorithms attempts to infer the dynamics of any state-action pair from known state-action pairs before meeting it for sufficient times. We propose a new model-based method ca…

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…

We consider the problem of joint estimation of structured inverse covariance matrices. We perform the estimation using groups of measurements with different covariances of the same unknown structure. Assuming the inverse covariances to span a low dimensional linear subspace in the space of symmetric matrices, our aim i…

New algorithms for fair item allocation with limited copies.

New algorithm for reinforcement learning reduces complexity and guarantees convergence.