TSPO-PET effectively distinguishes PwMS from HC and differentiates MS subtypes, but radiotracer, quantification method, image analysis method, reference tissue, and region of interest significantly impact TSPO-PET outcomes and must be considered when designing and interpreting studies.
Arian Madani Neishaboori, M. Agarwal, Ally Kalinsky et al.· Neurology(R) neuroimmunology...· 0 citations
Recovering dynamical systems from noisy observations is a recurring challenge across scientific domains, including neuroscience and physics. Latent stochastic differential equations (SDEs) address this by modeling the system as an unobserved state that evolves according to a learnable SDE and generates the observations...
Henry D. Smith, Brian L. Trippe, Scott W. Linderman· 0 citations
We study the generalization of ridge-regularized nonlinear least-squares models via on-average algorithmic stability, deriving error bounds for local minimizers in terms of a data-dependent effective dimension that reflects the geometry of the gradient model at the trained parameters, through the empirical Jacobian Gra...
Ayub Kharel, Ilja Kuzborskij, Patrick Rebeschini et al.· 0 citations
This paper proposes a new formulation of functional Gaussian Process regression on manifolds, based on an Empirical Bayes approach, in the spatiotemporal random field context. We apply the machinery of tight Gaussian measures in separable Hilbert spaces, exploiting the invariance property of covariance kernels under th...
MD Ruiz-Medina, AE Madrid, A Torres-Signes et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Conformal prediction (CP) constructs uncertainty sets for model outputs with finite-sample coverage guarantees. Yet ranking scores is straightforward only when they are scalar-valued, limiting CP to real-valued scores or ad-hoc one-dimensional reductions. Vector-valued scores arise naturally in multi-output regression...
It is increasingly important to evaluate the characteristics of systems based on large language models (LLMs). Evaluations in this context often rely on a curated benchmark set of input prompts provided to the LLM, where the output for each prompt may be assigned a binary or ordinal score and the aggregation of scores...
Saatvik Kher, Shang Wu, Rachel Longjohn et al.· 0 citations
Meta-learning aims to leverage information across related tasks to improve prediction on unlabeled data for new tasks when only a small number of labeled observations are available ("few-shot" learning). Increased task diversity is often believed to enhance meta-learning by providing richer information across tasks. Ho...
Saptati Datta, Nicolas W. Hengartner, Yulia Pimonova et al.· 0 citations
Regression problems with continuous bounded outcomes frequently arise in statistical and machine learning applications, such as the analysis of rates and proportions. A central challenge in this setting is predicting the response at a new covariate value. Most of the existing literature has focused either on point pred...
Zhanli Wu, Fabrizio Leisen, F. Javier Rubio· 0 citations
We introduce a novel framework for decentralized projection-free optimization, extending projection-free methods to a broader class of upper-linearizable functions. Our approach leverages decentralized optimization techniques with the flexibility of upper-linearizable function frameworks, effectively generalizing tradi...
Yiyang Lu, Mohammad Pedramfar, Vaneet Aggarwal· 0 citations
Motivated by the success of modern flow-based generative models in modeling complex data, we study two-sample testing through the lens of flow-based methods. We propose the Zero-Flow Two-Sample Test (ZF2ST), built on the zero-flow criterion, which characterizes distributional equality through a time-reversal antisymmet...
Yakun Wang, Leyang Wang, Song Liu et al.· 0 citations
We study episodic reinforcement learning with fixed reward and transition functions, but with episode-dependent admissible action sets that are observed at the start of each episode. Performance is measured by cumulative regret against the episode-wise optimal value, $\sum_{k=1}^K [V^{*,M^k} - V^{\pi^k,M^k}]$, where $M...
The Expectation-Maximisation (EM) algorithm is a central tool in statistics and machine learning, widely used for latent-variable models such as Gaussian Mixture Models (GMMs). Despite its ubiquity, EM is typically treated as a non-differentiable black box, preventing its integration into modern learning pipelines wher...
Samuel Bo\"it\'e, Eloi Tanguy, Julie Delon et al.· 0 citations
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
