arXiv subjects

Łukasz Kidziński

Publications and source records attributed to Łukasz Kidziński.

15 recordsLinked to original sources

arXiv2026

Curated AI beats frontier LLMs at pharma asset discovery

General-purpose LLMs with web search are increasingly used to scout the competitive landscape of pharmaceutical pipelines. We benchmark Gosset -- an AI platform with a chat interface backed by curated target-, modality-, and indication-level drug-asset annotations -- against four frontier systems with web access (Claude Opus 4.7, GPT 5.5, Gemini 3.1 Pro, Perplexity sonar-pro) on ten niche oncology/immunology targets where most of the pipeline lives in the long tail of preclinical and Asian-developed assets. All five systems receive the same natural-language query and the same JSON output schema. Across 10 targets Gosset returns 3.2x more verified drugs per query than the best frontier system, at perfect precision and 100% recall against the cross-system union of verified drugs. The same curated index is exposed as a Gosset MCP server that any frontier model can call as a tool, suggesting that each of these systems can close most of the recall gap by swapping generic web search for a curated index behind the same chat interface.

cs.AI↗

arXiv2022

Generalized Matrix Factorization: efficient algorithms for fitting generalized linear latent variable models to large data arrays

Unmeasured or latent variables are often the cause of correlations between multivariate measurements, which are studied in a variety of fields such as psychology, ecology, and medicine. For Gaussian measurements, there are classical tools such as factor analysis or principal component analysis with a well-established theory and fast algorithms. Generalized Linear Latent Variable models (GLLVMs) generalize such factor models to non-Gaussian responses. However, current algorithms for estimating model parameters in GLLVMs require intensive computation and do not scale to large datasets with thousands of observational units or responses. In this article, we propose a new approach for fitting GLLVMs to high-dimensional datasets, based on approximating the model using penalized quasi-likelihood and then using a Newton method and Fisher scoring to learn the model parameters. Computationally, our method is noticeably faster and more stable, enabling GLLVM fits to much larger matrices than previously possible. We apply our method on a dataset of 48,000 observational units with over 2,000 observed species in each unit and find that most of the variability can be explained with a handful of factors. We publish an easy-to-use implementation of our proposed fitting algorithm.

cs.LG↗

arXiv2021

Modeling longitudinal data using matrix completion

In clinical practice and biomedical research, measurements are often collected sparsely and irregularly in time while the data acquisition is expensive and inconvenient. Examples include measurements of spine bone mineral density, cancer growth through mammography or biopsy, a progression of defective vision, or assessment of gait in patients with neurological disorders. Since the data collection is often costly and inconvenient, estimation of progression from sparse observations is of great interest for practitioners. From the statistical standpoint, such data is often analyzed in the context of a mixed-effect model where time is treated as both a fixed-effect (population progression curve) and a random-effect (individual variability). Alternatively, researchers analyze Gaussian processes or functional data where observations are assumed to be drawn from a certain distribution of processes. These models are flexible but rely on probabilistic assumptions, require very careful implementation, specific to the given problem, and tend to be slow in practice. In this study, we propose an alternative elementary framework for analyzing longitudinal data, relying on matrix completion. Our method yields estimates of progression curves by iterative application of the Singular Value Decomposition. Our framework covers multivariate longitudinal data, regression, and can be easily extended to other settings. As it relies on existing tools for matrix algebra it is efficient and easy to implement. We apply our methods to understand trends of progression of motor impairment in children with Cerebral Palsy. Our model approximates individual progression curves and explains 30% of the variability. Low-rank representation of progression trends enables identification of different progression trends in subtypes of Cerebral Palsy.

stat.ML↗

arXiv2020

Open source software for automatic subregional assessment of knee cartilage degradation using quantitative T2 relaxometry and deep learning

Objective: We evaluate a fully-automated femoral cartilage segmentation model for measuring T2 relaxation values and longitudinal changes using multi-echo spin echo (MESE) MRI. We have open sourced this model and corresponding segmentations. Methods: We trained a neural network to segment femoral cartilage from MESE MRIs. Cartilage was divided into 12 subregions along medial-lateral, superficial-deep, and anterior-central-posterior boundaries. Subregional T2 values and four-year changes were calculated using a musculoskeletal radiologist's segmentations (Reader 1) and the model's segmentations. These were compared using 28 held out images. A subset of 14 images were also evaluated by a second expert (Reader 2) for comparison. Results: Model segmentations agreed with Reader 1 segmentations with a Dice score of 0.85 +/- 0.03. The model's estimated T2 values for individual subregions agreed with those of Reader 1 with an average Spearman correlation of 0.89 and average mean absolute error (MAE) of 1.34 ms. The model's estimated four-year change in T2 for individual regions agreed with Reader 1 with an average correlation of 0.80 and average MAE of 1.72 ms. The model agreed with Reader 1 at least as closely as Reader 2 agreed with Reader 1 in terms of Dice score (0.85 vs 0.75) and subregional T2 values. Conclusions: We present a fast, fully-automated model for segmentation of MESE MRIs. Assessments of cartilage health using its segmentations agree with those of an expert as closely as experts agree with one another. This has the potential to accelerate osteoarthritis research.

cs.CV↗

arXiv2019

Modeling treatment events in disease progression

Ability to quantify and predict progression of a disease is fundamental for selecting an appropriate treatment. Many clinical metrics cannot be acquired frequently either because of their cost (e.g. MRI, gait analysis) or because they are inconvenient or harmful to a patient (e.g. biopsy, x-ray). In such scenarios, in order to estimate individual trajectories of disease progression, it is advantageous to leverage similarities between patients, i.e. the covariance of trajectories, and find a latent representation of progression. Most of existing methods for estimating trajectories do not account for events in-between observations, what dramatically decreases their adequacy for clinical practice. In this study, we develop a machine learning framework named Coordinatewise-Soft-Impute (CSI) for analyzing disease progression from sparse observations in the presence of confounding events. CSI is guaranteed to converge to the global minimum of the corresponding optimization problem. Experimental results also demonstrates the effectiveness of CSI using both simulated and real dataset.

stat.ML↗

arXiv2019

Google Street View image of a house predicts car accident risk of its resident

Road traffic injuries are a leading cause of death worldwide. Proper estimation of car accident risk is critical for appropriate allocation of resources in healthcare, insurance, civil engineering, and other industries. We show how images of houses are predictive of car accidents. We analyze 20,000 addresses of insurance company clients, collect a corresponding house image using Google Street View, and annotate house features such as age, type, and condition. We find that this information substantially improves car accident risk prediction compared to the state-of-the-art risk model of the insurance company and could be used for price discrimination. From this perspective, public availability of house images raises legal and social concerns, as they can be a proxy of ethnicity, religion and other sensitive data.

stat.AP↗

arXiv2019

Artificial Intelligence for Prosthetics - challenge solutions

In the NeurIPS 2018 Artificial Intelligence for Prosthetics challenge, participants were tasked with building a controller for a musculoskeletal model with a goal of matching a given time-varying velocity vector. Top participants were invited to describe their algorithms. In this work, we describe the challenge and present thirteen solutions that used deep reinforcement learning approaches. Many solutions use similar relaxations and heuristics, such as reward shaping, frame skipping, discretization of the action space, symmetry, and policy blending. However, each team implemented different modifications of the known algorithms by, for example, dividing the task into subtasks, learning low-level control, or by incorporating expert knowledge and using imitation learning.

cs.LG↗

arXiv2018

Learning to Run challenge solutions: Adapting reinforcement learning methods for neuromusculoskeletal environments

In the NIPS 2017 Learning to Run challenge, participants were tasked with building a controller for a musculoskeletal model to make it run as fast as possible through an obstacle course. Top participants were invited to describe their algorithms. In this work, we present eight solutions that used deep reinforcement learning approaches, based on algorithms such as Deep Deterministic Policy Gradient, Proximal Policy Optimization, and Trust Region Policy Optimization. Many solutions use similar relaxations and heuristics, such as reward shaping, frame skipping, discretization of the action space, symmetry, and policy blending. However, each of the eight teams implemented different modifications of the known algorithms.

cs.LG↗

arXiv2018

Learning to Run challenge: Synthesizing physiologically accurate motion using deep reinforcement learning

Synthesizing physiologically-accurate human movement in a variety of conditions can help practitioners plan surgeries, design experiments, or prototype assistive devices in simulated environments, reducing time and costs and improving treatment outcomes. Because of the large and complex solution spaces of biomechanical models, current methods are constrained to specific movements and models, requiring careful design of a controller and hindering many possible applications. We sought to discover if modern optimization methods efficiently explore these complex spaces. To do this, we posed the problem as a competition in which participants were tasked with developing a controller to enable a physiologically-based human model to navigate a complex obstacle course as quickly as possible, without using any experimental data. They were provided with a human musculoskeletal model and a physics-based simulation environment. In this paper, we discuss the design of the competition, technical difficulties, results, and analysis of the top controllers. The challenge proved that deep reinforcement learning techniques, despite their high computational cost, can be successfully employed as an optimization method for synthesizing physiologically feasible motion in high-dimensional biomechanical systems.

cs.AI↗

arXiv2017

SweetRS: Dataset for a recommender systems of sweets

Benchmarking recommender system and matrix completion algorithms could be greatly simplified if the entire matrix was known. We built a \url{sweetrs.org} platform with $77$ candies and sweets to rank. Over $2000$ users submitted over $44000$ grades resulting in a matrix with $28\%$ coverage. In this report, we give the full description of the environment and we benchmark the \textsc{Soft-Impute} algorithm on the dataset.

cs.IR↗

arXiv2017

Learning styles: Literature versus machine learning

Every teacher understands that different students benefit from different activities. Recent advances in data processing allow us to detect and use behavioral variability for adapting to a student. This approach allows us to optimize learning process but does not focus on understanding it. Conversely, classical findings in educational sciences allow us to understand the learner but are hard to embed in a large scale adaptive system. In this study we design and build a framework to investigate when the two approaches coincide.

cs.HC↗

arXiv2016

Principal component analysis of periodically correlated functional time series

Within the framework of functional data analysis, we develop principal component analysis for periodically correlated time series of functions. We define the components of the above analysis including periodic, operator-valued filters, score processes and the inversion formulas. We show that these objects are defined via convergent series under a simple condition requiring summability of the Hilbert-Schmidt norms of the filter coefficients, and that they poses optimality properties. We explain how the Hilbert space theory reduces to an approximate finite-dimensional setting which is implemented in a custom build R package. A data example and a simulation study show that the new methodology is superior to existing tools if the functional time series exhibit periodic characteristics.

stat.ME↗

arXiv2015

Dynamic Functional Principal Component

In this paper, we address the problem of dimension reduction for time series of functional data $(X_t\colon t\in\mathbb{Z})$. Such {\it functional time series} frequently arise, e.g., when a continuous-time process is segmented into some smaller natural units, such as days. Then each~$X_t$ represents one intraday curve. We argue that functional principal component analysis (FPCA), though a key technique in the field and a benchmark for any competitor, does not provide an adequate dimension reduction in a time-series setting. FPCA indeed is a {\it static} procedure which ignores the essential information provided by the serial dependence structure of the functional data under study. Therefore, inspired by Brillinger's theory of {\it dynamic principal components}, we propose a {\it dynamic} version of FPCA, which is based on a frequency-domain approach. By means of a simulation study and an empirical illustration, we show the considerable improvement the dynamic approach entails when compared to the usual static procedure.

math.ST↗

arXiv2015

Functional Time Series

The continuous advances in data collection and storage techniques allow us to observe and record real-life processes in great detail. Examples include financial transaction data, fMRI images, satellite photos, earths pollution distribution in time etc. Due to the high dimensionality of such data, classical statistical tools become inadequate and inefficient. The need for new methods emerges and one of the most prominent techniques in this context is functional data analysis (FDA). The main objective of this article is to present techniques of the analysis of temporal dependence in FDA. Such dependence occurs, for example, if the data consist of a continuous time process which has been cut into segments, days for instance. We are then in the context of so-called functional time series.

stat.ME↗

arXiv2014

A note on estimation in Hilbertian linear models

We study estimation and prediction in linear models where the response and the regressor variable both take values in some Hilbert space. Our main objective is to obtain consistency of a principal components based estimator for the regression operator under minimal assumptions. In particular, we avoid some inconvenient technical restrictions that have been used throughout the literature. We develop our theory in a time dependent setup which comprises as important special case the autoregressive Hilbertian model.

math.ST↗