arXiv research

Study approximates worst-case stock trading under uncertainty, quantifying sensitivity.

ISMCTS-BR learns best responses in large games, approximating worst-case performance.

Develops wcPCA for better low-rank approximations in heterogeneous domains.

Classifies worst approximable rational numbers using hyperbolic geometry.

It is well known that Sparse PCA (Sparse Principal Component Analysis) is NP-hard to solve exactly on worst-case instances. What is the complexity of solving Sparse PCA approximately? Our contributions include: 1) a simple and efficient algorithm that achieves an $n^{-1/3}$-approximation; 2) NP-hardness of approximatio…

New expressive losses improve adversarial robustness without sacrificing accuracy.

This paper analyzes how randomizing rewards in MBRL can improve performance without being overly optimistic.

New method assesses financial and cyber risks under uncertainty.

Numerical challenges inherent in algorithms for computing worst Value-at-Risk in homogeneous portfolios are identified and solutions as well as words of warning concerning their implementation are provided. Furthermore, both conceptual and computational improvements to the Rearrangement Algorithm for approximating wors…

Method identifies shifts leading to large model performance differences.

There has been a large amount of interest, both in the past and particularly recently, into the power of different families of universal approximators, e.g. ReLU networks, polynomials, rational functions. However, current research has focused almost exclusively on understanding this problem in a worst-case setting, e.g…

Study proposes worst+gap measure for better DG evaluation.

New algorithms improve causal graph discovery with adaptive interventions, even under worst-case interventional costs.

New framework identifies worst-case shifts for predictive resource allocation models.

Paper introduces DOO models to outperform SAA out-of-sample.

Improves neural network performance by enriching training dataset.

We consider robust optimization problems, where the goal is to optimize in the worst case over a class of objective functions. We develop a reduction from robust improper optimization to Bayesian optimization: given an oracle that returns $α$-approximate solutions for distributions over objectives, we compute a distrib…

Improved bounds for function approximation in nonlinear sets.

Proposes a new uncertain volatility model with worst-case scenario analysis.

Robust hypothesis testing designs a test for worst-case distributions using kernel methods.

Data-independent pruning method reduces neural network size with accuracy guarantees.

In this paper, we study the asymptotic behavior of Asian option prices in the worst case scenario under an uncertain volatility model. We give a procedure to approximate the Asian option prices with a small volatility interval. By imposing additional conditions on the boundary condition and cutting the obtained Black-S…

One popular method for dealing with large-scale data sets is sampling. For example, by using the empirical statistical leverage scores as an importance sampling distribution, the method of algorithmic leveraging samples and rescales rows/columns of data matrices to reduce the data size before performing computations on…

Paper proposes a new method for WDRO with local perturbations, achieving better accuracy.

The problem of biclustering consists of the simultaneous clustering of rows and columns of a matrix such that each of the submatrices induced by a pair of row and column clusters is as uniform as possible. In this paper we approximate the optimal biclustering by applying one-way clustering algorithms independently on t…

In this paper, we propose the uncertain volatility models with stochastic bounds. Like the regular uncertain volatility models, we know only that the true model lies in a family of progressively measurable and bounded processes, but instead of using two deterministic bounds, the uncertain volatility fluctuates between …

DRCS selects a subset of data to minimize worst-case test error under covariate shift.

This paper tackles worst-class error rate in classification tasks.

Submodular extensions of an energy function can be used to efficiently compute approximate marginals via variational inference. The accuracy of the marginals depends crucially on the quality of the submodular extension. To identify the best possible extension, we show an equivalence between the submodular extensions of…

This paper explores minimax-Bayes solutions for reinforcement learning problems.

Four algorithms improve sparse tensor BR1Approx with theoretical guarantees.

Paper proves higher-order flow matching preserves optimality in generative modeling.

The regularization path of the Lasso can be shown to be piecewise linear, making it possible to "follow" and explicitly compute the entire path. We analyze in this paper this popular strategy, and prove that its worst case complexity is exponential in the number of variables. We then oppose this pessimistic result to a…

Worst-Case Sensitivity measures model sensitivity to uncertainty set size.

MPNN improves on UniFL approximation with provable guarantees.

Paper solves DRO for continuous distributions with iterative algorithms.

The book explores alternatives to worst-case analysis for algorithm performance.

Neural operators solve families of 2BSDEs efficiently.

Worst-case risk measures refer to the calculation of the largest value for risk measures when only partial information of the underlying distribution is available. For the popular risk measures such as Value-at-Risk (VaR) and Conditional Value-at-Risk (CVaR), it is now known that their worst-case counterparts can be ev…

Paper improves worst-case regret bounds for RLSVI in reinforcement learning.

A new algorithm ThreeSieves maximizes submodular functions efficiently in streaming data.

Detects adversarial directions to make reinforcement learning policies more robust.

Optimizes bond portfolios to avoid worst-case losses.

Error bounds based on worst likely assignments use permutation tests to validate classifiers. Worst likely assignments can produce effective bounds even for data sets with 100 or fewer training examples. This paper introduces a statistic for use in the permutation tests of worst likely assignments that improves error b…

Federated learning is a communication-efficient training process that alternates between local training at the edge devices and averaging the updated local model at the central server. Nevertheless, it is impractical to achieve a perfect acquisition of the local models in wireless communication due to noise, which also…

New algorithm reduces worst-case sample complexity for learning best arm.

This paper calculates worst-case target semi-variances for uncertain losses.

We analyze MDL for binary classification, quantifying overfitting and underfitting.