arXiv:2602.01427v2 Announce Type: replace Abstract: Few-shot learning requires models to generalize under limited supervision while remaining robust to distribution shifts. Existing Sinkhorn Distributionally Robust Optimization (DRO) methods provide theoretical guarantees but rely on a fixed reference distribution, which limits their adaptability. We propose a Prototype-Guided Distributionally Robust Optimization (PG-DRO) framework that learns class-adaptive priors from abundant base data via hierarchical optimal transport and embeds them into the Sinkhorn DRO formulation. This design enables few-shot information to be organically […]

Ver mais

arXiv:2601.18788v1 Announce Type: cross Abstract: Unsupervised text segmentation is crucial because boundary labels are expensive, subjective, and often fail to transfer across domains and granularity choices. We propose Embed-KCPD, a training-free method that represents sentences as embedding vectors and estimates boundaries by minimizing a penalized KCPD objective. Beyond the algorithmic instantiation, we develop, to our knowledge, the first dependence-aware theory for KCPD under $m$-dependent sequences, a finite-memory abstraction of short-range dependence common in language. We prove an oracle […]

Ver mais

Key Highlights: As Bill Gates recently said, we all are living inside an AI bubble right now, which I believe is somehow reshaping the global tech landscape. SoftBank, a Japanese conglomerate, appears to have made sure that it is in the front row of this AI boom, all thanks to its massive alliance with OpenAI. As artificial intelligence continues to drive big investments and strategic bets across industrie, SoftBank Group has been doubling down on its commitment to […]

Ver mais

arXiv:2505.07676v2 Announce Type: replace Abstract: We propose a framework for transfer learning of discount curves across different fixed-income product classes. Motivated by challenges in estimating discount curves from sparse or noisy data, we extend kernel ridge regression (KR) to a vector-valued setting, formulating a convex optimization problem in a vector-valued reproducing kernel Hilbert space (RKHS). Each component of the solution corresponds to the discount curve implied by a specific product class. We introduce an additional regularization term motivated […]

Ver mais

arXiv:2602.15863v1 Announce Type: new Abstract: Recent studies have shown that Large Language Models (LLMs) can improve their reasoning performance through self-generated few-shot examples, achieving results comparable to manually curated in-context examples. However, the underlying mechanism behind these gains remains unclear, making it hard to decide when and how to apply the technique effectively. In this work, we argue that the key benefit arises not from the generated examples themselves but from the act of creating them. To validate […]

Ver mais

Catastrophic forgetting impairs the continuous learning of large language models. We propose Fisher-Guided Gradient Masking (FGGM), a framework that mitigates this by strategically selecting parameters for updates using diagonal Fisher Information. FGGM dynamically generates binary masks with adaptive thresholds, preserving critical parameters to balance stability and plasticity without requiring historical data. Unlike magnitude-based methods such as MIGU, our approach offers a mathematically principled parameter importance estimation. On the TRACE benchmark, FGGM shows a 9.6% relative improvement in retaining […]

Ver mais

arXiv:2602.16715v1 Announce Type: new Abstract: We explore the potential of Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Graph-based RAG (GraphRAG) for generating Design Structure Matrices (DSMs). We test these methods on two distinct use cases — a power screwdriver and a CubeSat with known architectural references — evaluating their performance on two key tasks: determining relationships between predefined components, and the more complex challenge of identifying components and their subsequent relationships. We measure the performance by assessing […]

Ver mais

The podcast explores the different types of artificial intelligence (AI) and their capabilities. It distinguishes between narrow AI (weak AI), which performs specific tasks, general AI (strong AI) with broad human-like cognitive abilities, and superintelligent AI (ASI), which surpasses human intelligence in all aspects. It also explores the AI categories based on functionality (e.g., reactive machines, limited memory, theory of mind), learning models (supervised, unsupervised, reinforcement, and deep learning), It exemplifies specific branches of AI like machine learning, […]

Ver mais

This paper addresses multidimensional tuning parameter selection in the context of “train-validate-test” and $K$-fold cross validation. A coarse grid search over tuning parameter space is used to initialize a descent method which then jointly optimizes over variables and tuning parameters. We study four regularized regression methods and develop the update equations for the corresponding descent algorithms. Experiments on both simulated and real-world datasets show that the method results in significant tuning parameter refinement.

Ver mais

arXiv:2406.04071v3 Announce Type: replace Abstract: Given an undirected measurement graph $mathcal{H} = ([n], mathcal{E})$, the classical angular synchronization problem consists of recovering unknown angles $theta_1^*,dots,theta_n^*$ from a collection of noisy pairwise measurements of the form $(theta_i^* – theta_j^*) mod 2pi$, for all ${i,j} in mathcal{E}$. This problem arises in a variety of applications, including computer vision, time synchronization of distributed networks, and ranking from pairwise comparisons. In this paper, we consider a dynamic version of this problem where […]

Ver mais