9 papers
Provably Efficient Reinforcement Learning in Continuous-Time Episodic MDPs with Poisson Decision Epochs
Kenny Guo, Valentio Iverson, Sahan Wijetunga +1
Many real-world reinforcement learning (RL) problems evolve in continuous time, where decisions occur at irregular, event-driven intervals rather than at fixed discrete steps. We s…
Robust Statistical Estimators with Bounded Empirical Sensitivity
Valentio Iverson, Gautam Kamath, Argyris Mouzakis +1
We introduce a new measure of robustness for statistical estimators, which we call \emph{empirical sensitivity}. An estimator has bounded empirical sensitivity if, with hi…
On the 3-adic Valuation of a Cubic Binomial Sum
Valentio Iverson
In this short note, we prove a conjecture recently posed by Alekseyev, Amdeberhan, Shallit, and Vukusic on the 3-adic valuation of a cubic binomial sum.
Learning Half-Spaces from Perturbed Contrastive Examples
Aryan Alavi Razavi Ravari, Farnam Mansouri, Yuxin Chen +3
We study learning under a two-step contrastive example oracle, as introduced by Mansouri et. al. (2025), where each queried (or sampled) labeled example is paired with an additiona…
Multiplicatively dependent integer vectors on a hyperplane
Muhammad Afifurrahman, Valentio Iverson, Gian Cordana Sanjaya
We establish several asymptotic formulae and upper bounds for the count of multiplicatively dependent integer vectors that lie on a fixed hyperplane and have bounded height. This w…
Optimal Differentially Private Sampling of Unbounded Gaussians
Valentio Iverson, Gautam Kamath, Argyris Mouzakis
We provide the first -sample algorithm for sampling from unbounded Gaussian distributions under the constraint of $\left(\varepsilon, δ\right…
Squarefree discriminants of polynomials with prime coefficients
Valentio Iverson, Gian Cordana Sanjaya, Xiaoheng Wang
In this paper, we consider the family of monic polynomials with prime coefficients and the family of all polynomials with prime coefficients. We determine the number of in e…
Mean and Variance Estimation Complexity in Arbitrary Distributions via Wasserstein Minimization
Valentio Iverson, Stephen Vavasis
Parameter estimation is a fundamental challenge in machine learning, crucial for tasks such as neural network weight fitting and Bayesian inference. This paper focuses on the compl…
LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport
Kyeongha Rho, Hyeongkeun Lee, Valentio Iverson +1
Automated audio captioning is a task that generates textual descriptions for audio content, and recent studies have explored using visual information to enhance captioning quality.…