Igor Podolak

Igor Podolak

Auto-generated profile, based on publicly available information

Igor Podolak

Faculty of Mathematics and Computer Science, Jagiellonian University, Poland

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 October 2023 in Neural Networks
Verified
Journal Article
Open access
BWBartosz Wójcik
Bartosz Wójcik
MPMarcin Przewiȩźlikowski
Marcin Przewiȩźlikowski
FSFilip Szatkowski
Filip Szatkowski
MWMaciej Wołczyk
Maciej Wołczyk
KBKlaudia Bałazy
Klaudia Bałazy
Tomasz TrzcinskiTomasz Trzcinski
Tomasz Trzcinski
The problem of reducing processing time of large deep learning models is a fundamental challenge in many real-world applications. Early exit methods strive towards this goal by attaching additional Internal Classifiers (ICs) to intermediate layers of a neural network. ICs can quickly return predictions for easy examples and, as a result, reduce the average inference time of the whole model. However, if a particular IC does not decide to return an answer early, its predictions are discarded, with its computations effectively being wasted. To solve this issue, we introduce Zero Time Waste (ZTW), a novel approach in which each IC reuses predictions returned by its predecessors by (1) adding direct connections between ICs and (2) combining previous outputs in an ensemble-like manner. We conduct extensive experiments across various multiple modes, datasets, and architectures to demonstrate that ZTW achieves a significantly better accuracy vs. inference time trade-off than other early exit methods. On the ImageNet dataset, it obtains superior results over the best baseline method in 11 out of 16 cases, reaching up to 5 percentage points of improvement on low computational budgets.

10 March 2023 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
ŁSŁukasz Struski
Łukasz Struski
MSMichał Sadowski
Michał Sadowski
TDTomasz Danel
Tomasz Danel
JTJacek Tabor
Jacek Tabor
IPIgor T. Podolak
Igor T. Podolak
Interpolating between points is a problem connected simultaneously with finding geodesics and study of generative models. In the case of geodesics, we search for the curves with the shortest length, while in the case of generative models, we typically apply linear interpolation in the latent space. However, this interpolation uses implicitly the fact that Gaussian is unimodal. Thus, the problem of interpolating in the case when the latent density is non-Gaussian is an open problem. In this article, we present a general and unified approach to interpolation, which simultaneously allows us to search for geodesics and interpolating curves in latent space in the case of arbitrary density. Our results have a strong theoretical background based on the introduced quality measure of an interpolating curve. In particular, we show that maximizing the quality measure of the curve can be equivalently understood as a search of geodesic for a certain redefinition of the Riemannian metric on the space. We provide examples in three important cases. First, we show that our approach can be easily applied to finding geodesics on manifolds. Next, we focus our attention in finding interpolations in pretrained generative models. We show that our model effectively works in the case of arbitrary density. Moreover, we can interpolate in the subset of the space consisting of data possessing a given feature. The last case is focused on finding interpolation in the space of chemical compounds.

2 July 2019 in arXiv
Verified
Preprint
Open access
PDF file
SKSzymon Knop
Szymon Knop
JTJacek Tabor
Jacek Tabor
PSPrzemysław Spurek
Przemysław Spurek
IPIgor Podolak
Igor Podolak
MMMarcin Mazur
Marcin Mazur
SJStanisław JastrzęBski
Stanisław JastrzęBski
We propose a new generative model, Cramer-Wold Autoencoder (CWAE). Following WAE, we directly encourage normality of the latent space. Our paper uses also the recent idea from Sliced WAE (SWAE) model, which uses one-dimensional projections as a method of verifying closeness of two distributions. The crucial new ingredient is the introduction of a new (Cramer-Wold) metric in the space of densities, which replaces the Wasserstein metric used in SWAE. We show that the Cramer-Wold metric between Gaussian mixtures is given by a simple analytic formula, which results in the removal of sampling necessary to estimate the cost function in WAE and SWAE models. As a consequence, while drastically simplifying the optimization procedure, CWAE produces samples of a matching perceptual quality to other SOTA models.

28 September 2020 in PsyArXiv
Verified
Preprint
Open access
BBBartosz Bohaterewicz
Bartosz Bohaterewicz
MAMaria Sobczak Anna
Maria Sobczak Anna
IPIgor Podolak
Igor Podolak
BWBartosz Wójcik
Bartosz Wójcik
DMDagmara Mętel
Dagmara Mętel
TMTadeusz Marek
Tadeusz Marek
Background: Some studies suggest that as much as 40% of all causes of death in a group of patients with schizophrenia can be attributed to suicides and compared with the general population, patients with schizophrenia have an 8.5-fold greater suicide risk (SR). There is a vital need for accurate and reliable methods to predict the SR among patients with schizophrenia based on biological measures. However, it is unknown whether the suicidal risk in schizophrenia can be related to alterations in spontaneous brain activity, or if the resting-state functional magnetic resonance imaging (rsfMRI) measures can be used alongside machine learning (ML) algorithms in order to identify patients with SR.Methods: Fifty-nine participants including patients with schizophrenia with and without SR as well as age and gender-matched healthy underwent 13 minutes of resting-state functional magnetic resonance imaging. Both static and dynamic indexes of the amplitude of low-frequency fluctuation (ALFF), the fractional amplitude of low-frequency fluctuations (fALFF), regional homogeneity as well as functional connectivity (FC) was calculated and used as an input for five machine learning algorithms: Gradient boosting (GB), LASSO, Logistic Regression (LR), Random Forest and Support Vector Machine. Results: All groups revealed different internetwork functional connectivity in ventral DMN and anterior SN. The best performance was reached for the LASSO applied to FC with an accuracy of 70% and AUROC of 0.76 (p<0.05). Significant classification ability was also reached for GB and LR using fALFF and ALFF measures.Conclusion: Our findings suggest that SR in schizophrenia can be seen on the level of DMN and SN functional connectivity alterations. ML algorithms were able to significantly differentiate SR patients. Our results could be useful in developing neuromarkers of SR in schizophrenia based on non-invasive rsfMRI.