15 citations · 80 across the 20 of their papers we have counts for
20 papers
CodeTD: Topology of Attention Detects Hallucinations in Code LLMs
Daria Voronkova, Ilya Trofimov, Anton Dmitriev +3
As AI-code assistant tools become widespread, automatic assessment of the correctness of generated code becomes a significant challenge. Code LLMs are prone to hallucinations, whic…
Edge-wise Topological Divergence Gaps: Guiding Search in Combinatorial Optimization
Ilya Trofimov, Daria Voronkova, Alexander Mironenko +4
We introduce a topological feedback mechanism for the Travelling Salesman Problem (TSP) by analyzing the divergence between a tour and the minimum spanning tree (MST). Our key cont…
RTD-Lite: Scalable Topological Analysis for Comparing Weighted Graphs in Learning Tasks
Eduard Tulchinskii, Daria Voronkova, Ilya Trofimov +2
Topological methods for comparing weighted graphs are valuable in various learning tasks but often suffer from computational inefficiency on large datasets. We introduce RTD-Lite,…
Scalar Function Topology Divergence: Comparing Topology of 3D Objects
Ilya Trofimov, Daria Voronkova, Eduard Tulchinskii +2
We propose a new topological tool for computer vision - Scalar Function Topology Divergence (SFTD), which measures the dissimilarity of multi-scale topology between sublevel sets o…
SeqNAS: Neural Architecture Search for Event Sequence Classification
Igor Udovichenko, Egor Shvetsov, Denis Divitsky +6
Neural Architecture Search (NAS) methods are widely used in various industries to obtain high quality taskspecific solutions with minimal human intervention. Event Sequences find w…
Disentanglement Learning via Topology
Nikita Balabin, Daria Voronkova, Ilya Trofimov +2
We propose TopDis (Topological Disentanglement), a method for learning disentangled representations via adding a multi-scale topological loss term. Disentanglement is a crucial pro…
Learning Topology-Preserving Data Representations
Ilya Trofimov, Daniil Cherniavskii, Eduard Tulchinskii +3
We propose a method for learning topology-preserving data representations (dimensionality reduction). The method aims to provide topological similarity between the data manifold an…
Data-Driven Short-Term Daily Operational Sea Ice Regional Forecasting
Timofey Grigoryev, Polina Verezemskaya, Mikhail Krinitskiy +9
Global warming made the Arctic available for marine operations and created demand for reliable operational sea ice forecasts to make them safe. While ocean-ice numerical models are…
QuantNAS for super resolution: searching for efficient quantization-friendly architectures against quantization noise
Egor Shvetsov, Dmitry Osin, Alexey Zaytsev +4
There is a constant need for high-performing and computationally efficient neural network models for image super-resolution: computationally efficient models can be used via low-ca…
Representation Topology Divergence: A Method for Comparing Neural Network Representations
Serguei Barannikov, Ilya Trofimov, Nikita Balabin +1
Comparison of data representations is a complex multi-aspect problem that has not enjoyed a complete solution yet. We propose a method for comparing two data representations. We in…
Manifold Topology Divergence: a Framework for Comparing Data Manifolds
Serguei Barannikov, Ilya Trofimov, Grigorii Sotnikov +4
We develop a framework for comparing data manifolds, aimed, in particular, towards the evaluation of deep generative models. We describe a novel tool, Cross-Barcode(P,Q), that, giv…
Loss Barcode: A Topological Measure of Escapability in Loss Landscapes
Serguei Barannikov, Daria Voronkova, Alexander Mironenko +4
Neural network training is commonly based on SGD. However, the understanding of SGD's ability to converge to good local minima, given the non-convex nature of loss functions and th…
Optimizing the Neural Architecture of Reinforcement Learning Agents
N. Mazyavkina, S. Moustafa, I. Trofimov +1
Reinforcement learning (RL) enjoyed significant progress over the last years. One of the most important steps forward was the wide application of neural networks. However, architec…
NAS-Bench-NLP: Neural Architecture Search Benchmark for Natural Language Processing
Nikita Klyuchnikov, Ilya Trofimov, Ekaterina Artemova +3
Neural Architecture Search (NAS) is a promising and rapidly evolving research area. Training a large number of neural networks requires an exceptional amount of computational power…
Multi-fidelity Neural Architecture Search with Knowledge Distillation
Ilya Trofimov, Nikita Klyuchnikov, Mikhail Salnikov +2
Neural architecture search (NAS) targets at finding the optimal architecture of a neural network for a problem or a family of problems. Evaluations of neural architectures are very…
Inferring Complementary Products from Baskets and Browsing Sessions
Ilya Trofimov
Complementary products recommendation is an important problem in e-commerce. Such recommendations increase the average order price and the number of products in baskets. Complement…
LHCb trigger streams optimization
D. Derkach, N. Kazeev, R. Neychev +4
The LHCb experiment stores around collision events per year. A typical physics analysis deals with a final sample of up to events. Event preselection algorithms (l…
Distributed Coordinate Descent for Generalized Linear Models with Regularization
Ilya Trofimov, Alexander Genkin
Generalized linear model with and regularization is a widely used technique for solving classification, class probability estimation and regression problems. With the n…
Using Neural Networks for Click Prediction of Sponsored Search
Afroze Ibrahim Baqapuri, Ilya Trofimov
Sponsored search is a multi-billion dollar industry and makes up a major source of revenue for search engines (SE). click-through-rate (CTR) estimation plays a crucial role for ads…
Distributed Coordinate Descent for L1-regularized Logistic Regression
Ilya Trofimov, Alexander Genkin
Solving logistic regression with L1-regularization in distributed settings is an important problem. This problem arises when training dataset is very large and cannot fit the memor…