Search Results - "Konstantinov, Nikola"

Simplicity Bias of Two-Layer Networks beyond Linearly Separable Data by Tsoy, Nikita, Konstantinov, Nikola

“…Simplicity bias, the propensity of deep models to over-rely on simple features, has been identified as a potential reason for limited out-of-distribution…”
Get full text

Strategic Data Sharing between Competitors by Tsoy, Nikita, Konstantinov, Nikola

“…Collaborative learning techniques have significantly advanced in recent years, enabling private model training across multiple organizations. Despite this…”
Get full text

Fairness Through Regularization for Learning to Rank by Konstantinov, Nikola, Lampert, Christoph H

“…Given the abundance of applications of ranking in recent years, addressing fairness concerns around automated ranking systems becomes necessary for increasing…”
Get full text

Fairness-Aware PAC Learning from Corrupted Data by Konstantinov, Nikola, Lampert, Christoph H

“…Addressing fairness concerns about machine learning models is a crucial step towards their long-term adoption in real-world automated systems. While many…”
Get full text

Provable Mutual Benefits from Federated Learning in Privacy-Sensitive Domains by Tsoy, Nikita, Mihalkova, Anna, Todorova, Teodora, Konstantinov, Nikola

“…Cross-silo federated learning (FL) allows data owners to train accurate machine learning models by benefiting from each others private datasets. Unfortunately,…”
Get full text

Robust Learning from Untrusted Sources by Konstantinov, Nikola, Lampert, Christoph

“…Modern machine learning methods often require more data for training than a single expert can provide. Therefore, it has become a standard procedure to collect…”
Get full text

Incentivizing Honesty among Competitors in Collaborative Learning and Optimization by Dorner, Florian E, Konstantinov, Nikola, Pashaliev, Georgi, Vechev, Martin

“…Collaborative learning techniques have the potential to enable training machine learning models that are superior to models trained on a single entity's data…”
Get full text

FLEA: Provably Robust Fair Multisource Learning from Unreliable Training Data by Iofinova, Eugenia, Konstantinov, Nikola, Lampert, Christoph H

“…Fairness-aware learning aims at constructing classifiers that not only make accurate predictions, but also do not discriminate against specific groups. It is a…”
Get full text

Data Leakage in Federated Averaging by Dimitrov, Dimitar I, Balunović, Mislav, Konstantinov, Nikola, Vechev, Martin

“…Recent attacks have shown that user data can be recovered from FedSGD updates, thus breaking privacy. However, these attacks are of limited practical relevance…”
Get full text

COMPL-AI Framework: A Technical Interpretation and LLM Benchmarking Suite for the EU Artificial Intelligence Act by Guldimann, Philipp, Spiridonov, Alexander, Staab, Robin, Jovanović, Nikola, Vero, Mark, Vechev, Velko, Gueorguieva, Anna, Balunović, Mislav, Konstantinov, Nikola, Bielik, Pavol, Tsankov, Petar, Vechev, Martin

“…The EU's Artificial Intelligence Act (AI Act) is a significant step towards responsible AI development, but lacks clear technical interpretation, making it…”
Get full text

Human-Guided Fair Classification for Natural Language Processing by Dorner, Florian E, Peychev, Momchil, Konstantinov, Nikola, Goel, Naman, Ash, Elliott, Vechev, Martin

“…Text classifiers have promising applications in high-stake tasks such as resume screening and content moderation. These classifiers must be fair and avoid…”
Get full text

On the Sample Complexity of Adversarial Multi-Source PAC Learning by Konstantinov, Nikola, Frantar, Elias, Alistarh, Dan, Lampert, Christoph H

“…We study the problem of learning from multiple untrusted data sources, a scenario of increasing practical relevance given the recent emergence of crowdsourcing…”
Get full text

The Convergence of Stochastic Gradient Descent in Asynchronous Shared Memory by Alistarh, Dan, De Sa, Christopher, Konstantinov, Nikola

“…Stochastic Gradient Descent (SGD) is a fundamental algorithm in machine learning, representing the optimization backbone for training several classic models,…”
Get full text

The Convergence of Sparsified Gradient Methods by Alistarh, Dan, Hoefler, Torsten, Johansson, Mikael, Khirirat, Sarit, Konstantinov, Nikola, Renggli, Cédric

“…Distributed training of massive machine learning models, in particular deep neural networks, via Stochastic Gradient Descent (SGD) is becoming commonplace…”
Get full text

The human adenoid by Konstantinov, N, Golemanov, V

Get more information