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.
Paper discovers simplicial complexes connecting trained models for improved ensembling.
New insights into GNN optimization reveal skip connections and depth accelerate training.
New methods train neural networks without changing weights, achieving similar or higher performance.
Neuromorphic hardware tends to pose limits on the connectivity of deep networks that one can run on them. But also generic hardware and software implementations of deep learning run more efficiently for sparse networks. Several methods exist for pruning connections of a neural network after it was trained without conne…
Deep networks with a wide layer ensure sublevel set connectivity.
Unified framework for adaptive connection sampling in GNNs improves performance and robustness.
New algorithms reduce communication in GNN training.
Diagonal linear networks converge to lasso regularization path during training.
We draw a formal connection between using synthetic training data to optimize neural network parameters and approximate, Bayesian, model-based reasoning. In particular, training a neural network using synthetic data can be viewed as learning a proposal distribution generator for approximate inference in the synthetic-d…
Convolutional nets require fewer samples than fully-connected nets for image classification.
We propose Sparse Neural Network architectures that are based on random or structured bipartite graph topologies. Sparse architectures provide compression of the models learned and speed-ups of computations, they can also surpass their unstructured or fully connected counterparts. As we show, even more compact topologi…
The parameter server architecture is prevalently used for distributed deep learning. Each worker machine in a parameter server system trains the complete model, which leads to a hefty amount of network data transfer between workers and servers. We empirically observe that the data transfer has a non-negligible impact o…
ClusTR improves clustering-based models' robustness without adversarial training.
This work refines claims about neural network connectivity, showing that simultaneous linear connectivity is possible under certain conditions.
Mode connectivity is a recently introduced frame- work that empirically establishes the connected- ness of minima by finding a high accuracy curve between two independently trained models. To investigate the limits of this setup, we examine the efficacy of this technique in extreme cases where the input models are trai…
DCGANs generate drainage networks quickly from samples.
Geodesics connect model modes in neural network loss landscapes.
Paper studies ResNet dynamics using NTH, reducing width requirement.
Law derived for neural networks with sparse connections.
Study on dropout in neural networks using percolation theory.
We study whether a neural network optimizes to the same, linearly connected minimum under different samples of SGD noise (e.g., random data order and augmentation). We find that standard vision models become stable to SGD noise in this way early in training. From then on, the outcome of optimization is determined to a …
GT-DDP optimizer trains residual networks using game theory.
Recent efforts show that neural networks are vulnerable to small but intentional perturbations on input features in visual classification tasks. Due to the additional consideration of connections between examples (\eg articles with citation link tend to be in the same class), graph neural networks could be more sensiti…
Study proves existence of robust classifiers in multiclass adversarial training.
The loss functions of deep neural networks are complex and their geometric properties are not well understood. We show that the optima of these complex loss functions are in fact connected by simple curves over which training and test accuracy are nearly constant. We introduce a training procedure to discover these hig…
Spatial and visual connectivity are important metrics when developing workplace layouts. Calculating those metrics in real-time can be difficult, depending on the size of the floor plan being analysed and the resolution of the analyses. This paper investigates the possibility of considerably speeding up the outcomes of…
Improved GAN training stability through clipping and reweighting.
Trained recurrent networks are powerful tools for modeling dynamic neural computations. We present a target-based method for modifying the full connectivity matrix of a recurrent network to train it to perform tasks involving temporally complex input/output transformations. The method introduces a second network during…
Proposes using mode connectivity to improve adversarial robustness of neural networks.
In our previous work we have shown that resistive cross point devices, so called Resistive Processing Unit (RPU) devices, can provide significant power and speed benefits when training deep fully connected networks as well as convolutional neural networks. In this work, we further extend the RPU concept for training re…
Connections between nodes of fully connected neural networks are usually represented by weight matrices. In this article, functional transfer matrices are introduced as alternatives to the weight matrices: Instead of using real weights, a functional transfer matrix uses real functions with trainable parameters to repre…
Improvements in the performance of deep neural networks have often come through the design of larger and more complex networks. As a result, fast memory is a significant limiting factor in our ability to improve network performance. One approach to overcoming this limit is the design of sparse neural networks, which ca…
Improved NiNo networks accelerate Adam training by up to 50%.
In this paper, we propose a novel unsupervised learning method to learn the brain dynamics using a deep learning architecture named residual D-net. As it is often the case in medical research, in contrast to typical deep learning tasks, the size of the resting-state functional Magnetic Resonance Image (rs-fMRI) dataset…
DistGP models multi-robot mapping with distributed Gaussian process learning.
Nontrivial connectivity has allowed the training of very deep networks by addressing the problem of vanishing gradients and offering a more efficient method of reusing parameters. In this paper we make a comparison between residual networks, densely-connected networks and highway networks on an image classification tas…
Training large and highly accurate deep learning (DL) models is computationally costly. This cost is in great part due to the excessive number of trained parameters, which are well-known to be redundant and compressible for the execution phase. This paper proposes a novel transformation which changes the topology of th…
Novel 'strong neuron' improves deep learning efficiency and robustness.
We provide novel guaranteed approaches for training feedforward neural networks with sparse connectivity. We leverage on the techniques developed previously for learning linear networks and show that they can also be effectively adopted to learn non-linear networks. We operate on the moments involving label and the sco…
Enhances financial time-series prediction by adapting pre-trained models to new data.
The preponderance of connected devices provides unprecedented opportunities for fine-grained monitoring of the public infrastructure. However while classical models expect high quality application-specific data streams, the promise of the Internet of Things (IoT) is that of an abundance of disparate and noisy datasets …
Convolutional networks outperform fully-connected ones in certain tasks.
How can we build agents that keep learning from experience, quickly and efficiently, after their initial training? Here we take inspiration from the main mechanism of learning in biological brains: synaptic plasticity, carefully tuned by evolution to produce efficient lifelong learning. We show that plasticity, just li…
New methods connect low-loss points on neural network surfaces.
New limits found for training deep learning models efficiently.
One of the ways to train deep neural networks effectively is to use residual connections. Residual connections can be classified as being either identity connections or bridge-connections with a reshaping convolution. Empirical observations on CIFAR-10 and CIFAR-100 datasets using a baseline Resnet model, with bridge-c…
Many supervised learning tasks are emerged in dual forms, e.g., English-to-French translation vs. French-to-English translation, speech recognition vs. text to speech, and image classification vs. image generation. Two dual tasks have intrinsic connections with each other due to the probabilistic correlation between th…
The ability of deep neural networks to generalize well in the overparameterized regime has become a subject of significant research interest. We show that overparameterized autoencoders exhibit memorization, a form of inductive bias that constrains the functions learned through the optimization process to concentrate a…