A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Layer-wise networks have a closed-form solution and a stopping criterion.
Layer-wise networks have a closed-form solution and a stopping criterion.
Layer-wise preconditioning methods improve neural network optimization and feature learning.
A fundamental question in deep learning concerns the role played by individual layers in a deep neural network (DNN) and the transferable properties of the data representations which they learn. To the extent that layers have clear roles, one should be able to optimize them separately using layer-wise loss functions. S…
Automatically learns flexible symmetry constraints in neural networks using gradients.
Speeds up deep neural networks training by 10x using GPU concurrency.
Analyzes layer-wise quantization effects in neural networks.
Unified framework LPCD optimizes quantization of complex submodules.
Random layer-wise pruning profiles are as effective as metric-based ones for various datasets.
Study on shortcuts in deep networks, revealing their layer-wise distribution and impact.
This work analyzes how different layers in deep neural networks contribute to generalization error.
Pre-training is crucial for learning deep neural networks. Most of existing pre-training methods train simple models (e.g., restricted Boltzmann machines) and then stack them layer by layer to form the deep structure. This layer-wise pre-training has found strong theoretical foundation and broad empirical support. Howe…
In this paper, we tackle the problem of explanations in a deep-learning based model for recommendations by leveraging the technique of layer-wise relevance propagation. We use a Deep Convolutional Neural Network to extract relevant features from the input images before identifying similarity between the images in featu…
Model compression has been widely adopted to obtain light-weighted deep neural networks. Most prevalent methods, however, require fine-tuning with sufficient training data to ensure accuracy, which could be challenged by privacy and security issues. As a compromise between privacy and performance, in this paper we inve…
We propose a new optimization method for training feed-forward neural networks. By rewriting the activation function as an equivalent proximal operator, we approximate a feed-forward neural network by adding the proximal operators to the objective function as penalties, hence we call the lifted proximal operator machin…
We propose NovoGrad, an adaptive stochastic gradient descent method with layer-wise gradient normalization and decoupled weight decay. In our experiments on neural networks for image classification, speech recognition, machine translation, and language modeling, it performs on par or better than well tuned SGD with mom…
Deep neural networks have been used in various machine learning applications and achieved tremendous empirical successes. However, training deep neural networks is a challenging task. Many alternatives have been proposed in place of end-to-end back-propagation. Layer-wise training is one of them, which trains a single …
Improved bounds on neural network regions using activation histograms.
Proposes QEP to mitigate quantization error propagation in layer-wise post-training quantization.
We improve neural network explainability by bypassing batch normalization.
This paper uncovers the low-rank structure of neural network Hessians.
InteractionNet models noncovalent protein-ligand interactions with GNNs and explains predictions.
New method for efficient proximal mapping of 1-path-norm in shallow networks.
Drop-Muon updates only some layers, speeding up training.
A new method prevents forgetting during knowledge transfer.
Stochastic gradient descent (SGD) has achieved great success in training deep neural network, where the gradient is computed through back-propagation. However, the back-propagated values of different layers vary dramatically. This inconsistence of gradient magnitude across different layers renders optimization of deep …
Efficiently trains GCNs with reduced time and memory usage.
Low complexity decentralized neural net with centralized performance.
Supervised training of neural networks for classification is typically performed with a global loss function. The loss function provides a gradient for the output layer, and this gradient is back-propagated to hidden layers to dictate an update direction for the weights. An alternative approach is to train the network …
We propose a novel family of connectionist models based on kernel machines and consider the problem of learning layer-by-layer a compositional hypothesis class, i.e., a feedforward, multilayer architecture, in a supervised setting. In terms of the models, we present a principled method to "kernelize" (partly or complet…
We propose doubly nested network(DNNet) where all neurons represent their own sub-models that solve the same task. Every sub-model is nested both layer-wise and channel-wise. While nesting sub-models layer-wise is straight-forward with deep-supervision as proposed in \cite{xie2015holistically}, channel-wise nesting has…
LEWIS merges LLMs without training, improving performance on specific tasks.
Designs a neural network to reduce training cost by mapping to higher dimensions.
A well-conditioned Jacobian spectrum has a vital role in preventing exploding or vanishing gradients and speeding up learning of deep neural networks. Free probability theory helps us to understand and handle the Jacobian spectrum. We rigorously show almost sure asymptotic freeness of layer-wise Jacobians of deep neura…
Training of deep models for classification tasks is hindered by local minima problems and vanishing gradients, while unsupervised layer-wise pretraining does not exploit information from class labels. Here, we propose a new regularization technique, called diversifying regularization (DR), which applies a penalty on hi…
Various forms of representations may arise in the many layers embedded in deep neural networks (DNNs). Of these, where can we find the most compact representation? We propose to use a pruning framework to answer this question: How compact can each layer be compressed, without losing performance? Most of the existing DN…
New adversarial attack method based on deep feature distributions.
Large batch training improves deep learning performance without needing warmup.
New method improves accuracy of quantized neural networks.
Deep networks, composed of multiple layers of hierarchical distributed representations, tend to learn low-level features in initial layers and transition to high-level features towards final layers. Paradigms such as transfer learning, multi-task learning, and continual learning leverage this notion of generic hierarch…
This article proposes a communication-efficient decentralized deep learning algorithm, coined layer-wise federated group ADMM (L-FGADMM). To minimize an empirical risk, every worker in L-FGADMM periodically communicates with two neighbors, in which the periods are separately adjusted for different layers of its deep ne…
Recurrent Neural Networks (RNNs) achieve state-of-the-art results in many sequence-to-sequence modeling tasks. However, RNNs are difficult to train and tend to suffer from overfitting. Motivated by the Data Processing Inequality (DPI), we formulate the multi-layered network as a Markov chain, introducing a training met…
We combine supervised learning with unsupervised learning in deep neural networks. The proposed model is trained to simultaneously minimize the sum of supervised and unsupervised cost functions by backpropagation, avoiding the need for layer-wise pre-training. Our work builds on the Ladder network proposed by Valpola (…
A new method improves few-shot image classification by updating top layers.
Joslim optimizes both width and weight configurations for slimmable neural networks, improving model efficiency.
To reduce the long training time of large deep neural network (DNN) models, distributed synchronous stochastic gradient descent (S-SGD) is commonly used on a cluster of workers. However, the speedup brought by multiple workers is limited by the communication overhead. Two approaches, namely pipelining and gradient spar…
Backpropagation-free RL method trains layers using local signals.
We characterize convolutional neural networks with respect to the relative amount of features per layer. Using a skew normal distribution as a parametrized framework, we investigate the common assumption of monotonously increasing feature-counts with higher layers of architecture designs. Our evaluation on models with …