PaperMetrixEvidence-aware discovery
EN
Interface language English EN العربية AR Türkçe TR
Create account
Researcher profile

Mykola Pechenizkiy

7 papers in the PaperMetrix corpus

Publications

Papers by this author

  1. Controversy Rules - Discovering Regions Where Classifiers (Dis-)Agree Exceptionally

    2018 · arXiv (Cornell University)

    Finding regions for which there is higher controversy among different classifiers is insightful with regards to the domain and our models. Such evaluation can falsify assumptions, assert some, or also, bring to the attention unknown …

  2. Evolving Plasticity for Autonomous Learning under Changing Environmental Conditions

    2019 · University of Twente Research Information

    A fundamental aspect of learning in biological neural networks is the plasticity property which allows them to modify their configurations during their lifetime. Hebbian learning is a biologically plausible mechanism for modeling the plasticity property …

  3. The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training

    2022 · TU/e Research Portal

    Random pruning is arguably the most naive way to attain sparsity in neural networks, but has been deemed uncompetitive by either post-training pruning or sparse training. In this paper, we focus on sparse training and …

  4. Quick and Robust Feature Selection: the Strength of Energy-efficient\n Sparse Training for Autoencoders

    2020 · arXiv (Cornell University)

    Major complications arise from the recent increase in the amount of\nhigh-dimensional data, including high computational costs and memory\nrequirements. Feature selection, which identifies the most relevant and\ninformative attributes of a dataset, has been introduced as a …

  5. Provably Efficient Exploration in Constrained Reinforcement Learning:Posterior Sampling Is All You Need

    2023 · arXiv (Cornell University)

    We present a new algorithm based on posterior sampling for learning in constrained Markov decision processes (CMDP) in the infinite-horizon undiscounted setting. The algorithm achieves near-optimal regret bounds while being advantageous empirically compared to the …

  6. Heterophily-Based Graph Neural Network for Imbalanced Classification

    2023 · arXiv (Cornell University)

    Graph neural networks (GNNs) have shown promise in addressing graph-related problems, including node classification. However, conventional GNNs assume an even distribution of data across classes, which is often not the case in real-world scenarios, where …

  7. Addressing the Collaboration Dilemma in Low-Data Federated Learning via Transient Sparsity

    2025 · arXiv (Cornell University)

    Federated learning (FL) enables collaborative model training across decentralized clients while preserving data privacy, leveraging aggregated updates to build robust global models. However, this training paradigm faces significant challenges due to data heterogeneity and limited …