Search Results for author:
Found 16 papers, 11 papers with code
SeqNAS: Neural Architecture Search for Event Sequence Classification
As a result of our work we demonstrate that our method surpasses state of the art NAS methods and popular architectures suitable for sequence classification and holds great potential for various industrial applications.
Disentanglement Learning via Topology
We propose TopDis (Topological Disentanglement), a method for learning disentangled representations via adding multi-scale topological loss term.
Learning Topology-Preserving Data Representations
The method aims to provide topological similarity between the data manifold and its latent representation via enforcing the similarity in topological features (clusters, loops, 2D voids, etc.)
Data-Driven Short-Term Daily Operational Sea Ice Regional Forecasting
Global warming made the Arctic available for marine operations and created demand for reliable operational sea ice forecasts to make them safe.
QuantNAS for super resolution: searching for efficient quantization-friendly architectures against quantization noise
The approach utilizes entropy regularization, quantization noise, and Adaptive Deviation for Quantization (ADQ) module to enhance the search procedure.
Representation Topology Divergence: A Method for Comparing Neural Network Representations
Comparison of data representations is a complex multi-aspect problem that has not enjoyed a complete solution yet.
Representation Topology Divergence: A Method for Comparing Neural Network Representations.
We propose a method for comparing two data representations.
Manifold Topology Divergence: a Framework for Comparing Data Manifolds
We develop a framework for comparing data manifolds, aimed, in particular, towards the evaluation of deep generative models.
Manifold Topology Divergence: a Framework for Comparing Data Manifolds.
We propose a framework for comparing data manifolds, aimed, in particular, towards the evaluation of deep generative models.
Topological obstructions in neural networks learning
We define the neural network Topological Obstructions score, "TO-score", with the help of robust topological invariants, barcodes of the loss function, that quantify the "badness" of local minima for gradient-based optimization.
Multi-fidelity Neural Architecture Search with Knowledge Distillation
The method relies on a new approach to low-fidelity evaluations of neural architectures by training for a few epochs using a knowledge distillation.
NAS-Bench-NLP: Neural Architecture Search Benchmark for Natural Language Processing
In this work, we step outside the computer vision domain by leveraging the language modeling task, which is the core of natural language processing (NLP).
Inferring Complementary Products from Baskets and Browsing Sessions
These vector representations are used for making complementary products recommendation.
Distributed Coordinate Descent for Generalized Linear Models with Regularization
Generalized linear model with $L_1$ and $L_2$ regularization is a widely used technique for solving classification, class probability estimation and regression problems.
Using Neural Networks for Click Prediction of Sponsored Search
Sponsored search is a multi-billion dollar industry and makes up a major source of revenue for search engines (SE).
Distributed Coordinate Descent for L1-regularized Logistic Regression
Solving logistic regression with L1-regularization in distributed settings is an important problem.
