Renat Sergazinov

Renat Sergazinov, Mohammadreza Armandpour, Irina Gaynanova

Deep learning models achieve state-of-the art results in predicting blood glucose trajectories, with a wide range of architectures being proposed. However, the adaptation of such models in clinical practice is slow, largely due to the lack of uncertainty quantification of provided predictions. In this work, we propose to model the future glucose trajectory conditioned on the past as an infinite mixture of basis distributions (i.e., Gaussian, Laplace, etc.). This change allows us to learn the uncertainty and predict more accurately in the cases when the trajectory has a heterogeneous or multi-modal distribution. To estimate the parameters of the predictive distribution, we utilize the Transformer architecture. We empirically demonstrate the superiority of our method over existing state-of-the-art techniques both in terms of accuracy and uncertainty on the synthetic and benchmark glucose data sets.

Renat Sergazinov, Shao-An Yin

TabPFN v2 achieves better results than tree-based models on several tabular benchmarks, which is notable since tree-based models are usually the strongest choice for tabular data. However, it cannot handle more than 10K context tokens because transformers have quadratic computation and memory costs. Unlike existing approaches that rely on context compression, such as selecting representative samples via K-nearest neighbors (KNN), we introduce a tiled-block strategy to compute attention within the TabPFN framework. This design is compatible with standard GPU setups and, to the best of our knowledge, is the first to enable TabPFN to process long contexts without any pre-processing. We demonstrate the effectiveness of our approach on the standard TabArena benchmark, with code available at https://github.com/mrsergazinov/chunk_tabpfn.

Jing Wu, Suiyao Chen, Qi Zhao et al.

Self-supervised representation learning methods have achieved significant success in computer vision and natural language processing, where data samples exhibit explicit spatial or semantic dependencies. However, applying these methods to tabular data is challenging due to the less pronounced dependencies among data samples. In this paper, we address this limitation by introducing SwitchTab, a novel self-supervised method specifically designed to capture latent dependencies in tabular data. SwitchTab leverages an asymmetric encoder-decoder framework to decouple mutual and salient features among data pairs, resulting in more representative embeddings. These embeddings, in turn, contribute to better decision boundaries and lead to improved results in downstream tasks. To validate the effectiveness of SwitchTab, we conduct extensive experiments across various domains involving tabular data. The results showcase superior performance in end-to-end prediction tasks with fine-tuning. Moreover, we demonstrate that pre-trained salient embeddings can be utilized as plug-and-play features to enhance the performance of various traditional classification methods (e.g., Logistic Regression, XGBoost, etc.). Lastly, we highlight the capability of SwitchTab to create explainable representations through visualization of decoupled mutual and salient features in the latent space.

Renat Sergazinov, Armeen Taeb, Irina Gaynanova

Multi-view data provides complementary information on the same set of observations, with multi-omics and multimodal sensor data being common examples. Analyzing such data typically requires distinguishing between shared (joint) and unique (individual) signal subspaces from noisy, high-dimensional measurements. Despite many proposed methods, the conditions for reliably identifying joint and individual subspaces remain unclear. We rigorously quantify these conditions, which depend on the ratio of the signal rank to the ambient dimension, principal angles between true subspaces, and noise levels. Our approach characterizes how spectrum perturbations of the product of projection matrices, derived from each view's estimated subspaces, affect subspace separation. Using these insights, we provide an easy-to-use and scalable estimation algorithm. In particular, we employ rotational bootstrap and random matrix theory to partition the observed spectrum into joint, individual, and noise subspaces. Diagnostic plots visualize this partitioning, providing practical and interpretable insights into the estimation performance. In simulations, our method estimates joint and individual subspaces more accurately than existing approaches. Applications to multi-omics data from colorectal cancer patients and nutrigenomic study of mice demonstrate improved performance in downstream predictive tasks.

George Yakushev, Alina Shutova, Ivan Rubachev et al.

Tabular foundation models are becoming increasingly popular for low-resource tabular problems. These models make up for small training datasets by pretraining on large volumes of synthetic data. The prior knowledge obtained via pretraining provides the exceptional performance, but the resulting model becomes a black box that is difficult to interpret and costly to inference. In this work, we explore an alternative strategy: using reasoning-capable LLMs to induce decision trees for small tabular datasets in agentic setup. We design a minimal set of tools for constructing, analyzing and manipulating decision trees. By using these tools, LLMs combine their prior knowledge with learning from data to create a lightweight decision tree that outperforms traditional CART on low-resource tabular problems. While a single decision tree does not outperform state-of-the-art black box models, it comes with a human-readable reasoning trace that can be checked for biases and data leaks. Furthermore, the reasoning-based LLM's creation process allows for additional human input: correcting biases or incorporating domain-specific intuition that is not captured in the data.

Renat Sergazinov, Jing Wu, Shao-An Yin

While random Fourier features are a classic tool in kernel methods, their utility as a pre-processing step for deep learning on tabular data has been largely overlooked. Motivated by shortcomings in tabular deep learning pipelines - revealed through Neural Tangent Kernel (NTK) analysis - we revisit and repurpose random Fourier mappings as a parameter-free, architecture-agnostic transformation. By projecting each input into a fixed feature space via sine and cosine projections with frequencies drawn once at initialization, this approach circumvents the need for ad hoc normalization or additional learnable embeddings. We show within the NTK framework that this mapping (i) bounds and conditions the network's initial NTK spectrum, and (ii) introduces a bias that shortens the optimization trajectory, thereby accelerating gradient-based training. These effects pre-condition the network with a stable kernel from the outset. Empirically, we demonstrate that deep networks trained on Fourier-transformed inputs converge more rapidly and consistently achieve strong final performance, often with fewer epochs and less hyperparameter tuning. Our findings establish random Fourier pre-processing as a theoretically motivated, plug-and-play enhancement for tabular deep learning.

Renat Sergazinov, Miroslav Kramar

Photoelastic techniques have a long tradition in both qualitative and quantitative analysis of the stresses in granular materials. Over the last two decades, computational methods for reconstructing forces between particles from their photoelastic response have been developed by many different experimental teams. Unfortunately, all of these methods are computationally expensive. This limits their use for processing extensive data sets that capture the time evolution of granular ensembles consisting of a large number of particles. In this paper, we present a novel approach to this problem which leverages the power of convolutional neural networks to recognize complex spatial patterns. The main drawback of using neural networks is that training them usually requires a large labeled data set which is hard to obtain experimentally. We show that this problem can be successfully circumvented by pretraining the networks on a large synthetic data set and then fine-tuning them on much smaller experimental data sets. Due to our current lack of experimental data, we demonstrate the potential of our method by changing the size of the considered particles which alters the exhibited photoelastic patterns more than typical experimental errors.