Search Results for author:
Found 13 papers, 6 papers with code
Large Learning Rates Improve Generalization: But How Large Are We Talking About?
Inspired by recent research that recommends starting neural networks training with large learning rates (LRs) to achieve the best generalization, we explore this hypothesis in detail.
Training Scale-Invariant Neural Networks on the Sphere Can Happen in Three Regimes
In this work, we investigate the properties of training scale-invariant neural networks directly on the sphere using a fixed ELR.
Machine Learning Methods for Spectral Efficiency Prediction in Massive MIMO Systems
Channel decoding, channel detection, channel assessment, and resource management for wireless multiple-input multiple-output (MIMO) systems are all examples of problems where machine learning (ML) can be successfully applied.
On the Memorization Properties of Contrastive Learning
Memorization studies of deep neural networks (DNNs) help to understand what patterns and how do DNNs learn, and motivate improvements to DNN training approaches.
On the Periodic Behavior of Neural Network Training with Batch Normalization and Weight Decay
Training neural networks with batch normalization and weight decay has become a common practice in recent years.
On Power Laws in Deep Ensembles
Ensembles of deep neural networks are known to achieve state-of-the-art performance in uncertainty estimation and lead to accuracy improvement.
Deep Ensembles on a Fixed Memory Budget: One Wide Network or Several Thinner Ones?
In this work, we consider a fixed memory budget setting, and investigate, what is more effective: to train a single wide network, or to perform a memory split -- to train an ensemble of several thinner networks, with the same total number of parameters?
Structured Sparsification of Gated Recurrent Neural Networks
Recently, a lot of techniques were developed to sparsify the weights of neural networks and to remove networks' structure units, e. g. neurons.
Bayesian Sparsification of Gated Recurrent Neural Networks
Bayesian methods have been successfully applied to sparsify weights of neural networks and to remove structure units from the networks, e. g. neurons.
Bayesian Compression for Natural Language Processing
In natural language processing, a lot of the tasks are successfully solved with recurrent neural networks, but such models have a huge number of parameters.
Semantic embeddings for program behavior patterns
In this paper, we propose a new feature extraction technique for program execution logs.
Bayesian Sparsification of Recurrent Neural Networks
Recurrent neural networks show state-of-the-art results in many text analysis tasks but often require a lot of memory to store their weights.
Joint Optimization of Segmentation and Color Clustering
We propose to make clustering an integral part of segmentation, by including a new clustering term in the energy function.
