Model interpretability through the lens of computational complexity
In spite of several claims stating that some models are more interpretable than others--eg,"
linear models are more interpretable than deep neural networks"--we still lack a principled …
linear models are more interpretable than deep neural networks"--we still lack a principled …
On computing probabilistic abductive explanations
The most widely studied explainable AI (XAI) approaches are unsound. This is the case with
well-known model-agnostic explanation approaches, and it is also the case with approaches …
well-known model-agnostic explanation approaches, and it is also the case with approaches …
A simple near-linear pseudopolynomial time randomized algorithm for subset sum
Given a multiset $ S $ of $ n $ positive integers and a target integer $ t $, the Subset Sum
problem asks to determine whether there exists a subset of $ S $ that sums up to $ t $. The …
problem asks to determine whether there exists a subset of $ S $ that sums up to $ t $. The …
On computing relevant features for explaining NBCs
Despite the progress observed with model-agnostic explainable AI (XAI), it is the case that
model-agnostic XAI can produce incorrect explanations. One alternative are the so-called …
model-agnostic XAI can produce incorrect explanations. One alternative are the so-called …
Strongly polynomial FPTASes for monotone dynamic programs
T Alon, N Halman - Algorithmica, 2022 - Springer
In this paper we introduce a framework for the automatic generation of Strongly Polynomial
Fully Polynomial Time Approximation Schemes (SFPTASes) for monotone dynamic …
Fully Polynomial Time Approximation Schemes (SFPTASes) for monotone dynamic …
Fully Polynomial Time Approximation Schemes for Robust Multistage Decision Making
N Halman, G Nannicini - INFORMS Journal on Computing, 2024 - pubsonline.informs.org
We design a framework to obtain Fully Polynomial Time Approximation Schemes (FPTASes)
for adjustable robust multistage decision making under the budgeted uncertainty sets …
for adjustable robust multistage decision making under the budgeted uncertainty sets …
Approximately Counting Knapsack Solutions in Subquadratic Time
We revisit the classic# Knapsack problem, which asks to count the Boolean points (x 1, x
2,…, xn)∈{0, 1} n in a given half-space. This# P-complete problem is known to admit (1±∊) …
2,…, xn)∈{0, 1} n in a given half-space. This# P-complete problem is known to admit (1±∊) …
Synthetic Census Data Generation via Multidimensional Multiset Sum
The US Decennial Census provides valuable data for both research and policy purposes.
Census data are subject to a variety of disclosure avoidance techniques prior to release in …
Census data are subject to a variety of disclosure avoidance techniques prior to release in …
Probability estimation via policy restrictions, convexification, and approximate sampling
This paper develops various optimization techniques to estimate probability of events where
the optimal value of a convex program, satisfying certain structural assumptions, exceeds a …
the optimal value of a convex program, satisfying certain structural assumptions, exceeds a …
Games with Weighted Multiple Objectives
O Kupferman, N Shenwald - … on Automated Technology for Verification and …, 2024 - Springer
Games with multiple objectives arise naturally in synthesis of reactive systems. We study
games with weighted multiple objectives. The winning objective in such games consists of a …
games with weighted multiple objectives. The winning objective in such games consists of a …