Related papers: HELOC Applicant Risk Performance Evaluation by Top…

We present a method for performing hierarchical object detection in images guided by a deep reinforcement learning agent. The key idea is to focus on those parts of the image that contain richer information and zoom on them. We train an…

In graph signal processing, learning the weighted connections between nodes from a set of sample signals is a fundamental task when the underlying relationships are not known a priori. This task is typically addressed by finding a graph…

Given an unsupervised outlier detection (OD) algorithm, how can we optimize its hyperparameter(s) (HP) on a new dataset, without any labels? In this work, we address this challenging hyperparameter optimization for unsupervised OD problem,…

The purpose of this master's thesis is to study and develop a new algorithmic framework for collaborative filtering (CF) to generate recommendations. The method we propose is based on the exploitation of the hierarchical structure of the…

Deep learning has significantly advanced time series forecasting through its powerful capacity to capture sequence relationships. However, training these models with the Mean Square Error (MSE) loss often results in over-smooth predictions,…

Real-world data is complex and often consists of objects that can be decomposed into multiple entities (e.g. images into pixels, graphs into interconnected nodes). Randomized smoothing is a powerful framework for making models provably…

We study policy evaluation problems in multi-task reinforcement learning (RL) under a low-rank representation setting. In this setting, we are given $N$ learning tasks where the corresponding value function of these tasks lie in an…

We consider decentralized model training in tiered communication networks. Our network model consists of a set of silos, each holding a vertical partition of the data. Each silo contains a hub and a set of clients, with the silo's vertical…

MPI applications matter. However, with the advent of many-core processors, traditional MPI applications are challenged to achieve satisfactory performance. This is due to the inability of these applications to respond to load imbalances, to…

With the growing adoption of AI-based systems across everyday life, the need to understand their decision-making mechanisms is correspondingly increasing. The level at which we can trust the statistical inferences made from AI-based…

Deep learning has recently demonstrated its ability to rival the human brain for visual object recognition. As datasets get larger, a natural question to ask is if existing deep learning architectures can be extended to handle the 50+K…

Mechanistic interpretability seeks to reverse-engineer neural network computations into human-understandable algorithms, yet extracting sparse computational circuits from billion-parameter language models remains challenging due to…

Deploying deep neural networks for risk-sensitive tasks necessitates an uncertainty estimation mechanism. This paper introduces hierarchical selective classification, extending selective classification to a hierarchical setting. Our…

A central problem in topological data analysis is that of computing the homology of a given simplicial complex. Said complexes can have arbitrary large number of simplices, as can happen, for example, if the space is the Rips-Vietoris or…

Hierarchical Reinforcement Learning (HRL) allows interactive agents to decompose complex problems into a hierarchy of sub-tasks. Higher-level tasks can invoke the solutions of lower-level tasks as if they were primitive actions. In this…

This paper presents a novel credit scoring approach using neural networks to address class imbalance and out-of-time prediction challenges. We develop a specific optimizer and loss function inspired by Hamiltonian mechanics that better…

Current federated-learning models deteriorate under heterogeneous (non-I.I.D.) client data, as their feature representations diverge and pixel- or patch-level objectives fail to capture the global topology which is essential for…

Traditional risk measures in finance, predominantly based on the second moment of return distributions or tail risk heuristics (VaR/CVaR), fail to account for the intrinsic geometric structure of market dynamics. This paper introduces a…

Hierarchical classification offers an approach to incorporate the concept of mistake severity by leveraging a structured, labeled hierarchy. However, decoding in such settings frequently relies on heuristic decision rules, which may not…

Event reconstruction at the LHC, the task of assigning observed physics objects to their true origins, is a central challenge for precision measurements and searches. Many existing machine learning approaches address this problem but rely…