Tootfinder

Poisoning Prevention in Federated Learning and Differential Privacy via Stateful Proofs of Execution
Norrathep Rattanavipanon, Ivan de Oliviera Nunes
https://arxiv.org/abs/2404.06721

Poisoning Prevention in Federated Learning and Differential Privacy via Stateful Proofs of Execution
The rise in IoT-driven distributed data analytics, coupled with increasing privacy concerns, has led to a demand for effective privacy-preserving and federated data collection/model training mechanisms. In response, approaches such as Federated Learning (FL) and Local Differential Privacy (LDP) have been proposed and attracted much attention over the past few years. However, they still share the common limitation of being vulnerable to poisoning attacks wherein adversaries compromising edge dev…

Teleoscope: Exploring Themes in Large Document Sets By Example
Paul Bucci, Leo Foord-Kelcey, Patrick Yung Kang Lee, Alamjeet Singh, Ivan Beschastnikh
https://arxiv.org/abs/2402.06124

Teleoscope: Exploring Themes in Large Document Sets By Example
Qualitative thematic exploration of data by hand does not scale and researchers create and update a personalized point of view as they explore data. As a result, machine learning (ML) approaches that might help with exploration are challenging to apply. We developed Teleoscope, a web-based system that supports interactive exploration of large corpora (100K-1M) of short documents (1-3 paragraphs). Teleoscope provides visual programming workflows that have semantic and computational meaning; help…

Stability-Certified On-Policy Data-Driven LQR via Recursive Learning and Policy Gradient
Lorenzo Sforni, Guido Carnevale, Ivano Notarnicola, Giuseppe Notarstefano
https://arxiv.org/abs/2403.05367

Stability-Certified On-Policy Data-Driven LQR via Recursive Learning and Policy Gradient
In this paper, we investigate a data-driven framework to solve Linear Quadratic Regulator (LQR) problems when the dynamics is unknown, with the additional challenge of providing stability certificates for the overall learning and control scheme. Specifically, in the proposed on-policy learning framework, the control input is applied to the actual (unknown) linear system while iteratively optimized. We propose a learning and control procedure, termed RELEARN LQR, that combines a recursive least …

I need to spend some minutes on learning to use a better camera app on my iPhone. It is so annoying when the system camera app keeps focusing on the dirt on train windows.

CALRec: Contrastive Alignment of Generative LLMs For Sequential Recommendation
Yaoyiran Li, Xiang Zhai, Moustafa Alzantot, Keyi Yu, Ivan Vuli\'c, Anna Korhonen, Mohamed Hammad
https://arxiv.org/abs/2405.02429

CALRec: Contrastive Alignment of Generative LLMs For Sequential Recommendation
Traditional recommender systems such as matrix factorization methods rely on learning a shared dense embedding space to represent both items and user preferences. Sequence models such as RNN, GRUs, and, recently, Transformers have also excelled in the task of sequential recommendation. This task requires understanding the sequential structure present in users' historical interactions to predict the next item they may like. Building upon the success of Large Language Models (LLMs) in a variety o…

Cross-Platform Autonomous Control of Minimal Kitaev Chains
David van Driel, Rouven Koch, Vincent P. M. Sietses, Sebastiaan L. D. ten Haaf, Chun-Xiao Liu, Francesco Zatelli, Bart Roovers, Alberto Bordin, Nick van Loo, Guanzhong Wang, Jan Cornelis Wolff, Grzegorz P. Mazur, Tom Dvir, Ivan Kulesh, Qingzhen Wang, A. Mert Bozkurt, Sasa Gazibegovic, Ghada Badawy, Erik P. A. M. Bakkers, Michael Wimmer, Srijit Goswami, Jose L. Lado, Leo P. Kouwenhoven, Eliska Greplova

Cross-Platform Autonomous Control of Minimal Kitaev Chains
Contemporary quantum devices are reaching new limits in size and complexity, allowing for the experimental exploration of emergent quantum modes. However, this increased complexity introduces significant challenges in device tuning and control. Here, we demonstrate autonomous tuning of emergent Majorana zero modes in a minimal realization of a Kitaev chain. We achieve this task using cross-platform transfer learning. First, we train a tuning model on a theory model. Next, we retrain it using a …

What Impacts the Quality of the User Answers when Asked about the Current Context?
Ivano Bison, Haonan Zhao, Fausto Giunchiglia
https://arxiv.org/abs/2405.04054

What Impacts the Quality of the User Answers when Asked about the Current Context?
Sensor data provide an objective view of reality but fail to capture the subjective motivations behind an individual's behavior. This latter information is crucial for learning about the various dimensions of the personal context, thus increasing predictability. The main limitation is the human input, which is often not of the quality that is needed. The work so far has focused on the usually high number of missing answers. The focus of this paper is on \textit{the number of mistakes} made when…

@… Have you ever noticed variation in the tap strength required to click an iPhone? Sometimes a gentle (or accidental) brush with the side of your finger works, sometimes a firm straight down strike with the tip of your finger is required. Happens in Safari for a few predictable requests. Happens seemingly randomly in iOS Vivaldi. Maybe only on my tiny SE2020? I don…

A look at the US DOJ's lawsuit against Apple, comparisons to Microsoft suit in the 90's, basic factual errors, why it is clearly a political case, and more (Steven Sinofsky/Hardcore Software)
https://hardcoresoftware.learningbyshipping…

216. United States v. Apple (Complaint)
March 21, 2024 the United States filed an antitrust complaint against Apple. The filing is a new approach to antitrust and hinges on mostly how Apple chose to design the iPhone from the very start.

Multi-Objective Recommendation via Multivariate Policy Learning
Olivier Jeunen, Jatin Mandav, Ivan Potapov, Nakul Agarwal, Sourabh Vaid, Wenzhe Shi, Aleksei Ustimenko
https://arxiv.org/abs/2405.02141

Multi-Objective Recommendation via Multivariate Policy Learning
Real-world recommender systems often need to balance multiple objectives when deciding which recommendations to present to users. These include behavioural signals (e.g. clicks, shares, dwell time), as well as broader objectives (e.g. diversity, fairness). Scalarisation methods are commonly used to handle this balancing task, where a weighted average of per-objective reward signals determines the final score used for ranking. Naturally, how these weights are computed exactly, is key to success …