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.
This paper explores loss landscapes of sparse neural networks, finding unique characteristics compared to dense networks.
ARMA nets expand receptive fields for dense prediction tasks.
Sparse butterfly network replaces dense layers in neural networks, improving expressibility and performance.
Dense neural networks can't approximate all functions.
This paper presents a new artificial neuron model capable of learning its receptive field in the topological domain of inputs. The model provides adaptive and differentiable local connectivity (plasticity) applicable to any domain. It requires no other tool than the backpropagation algorithm to learn its parameters whi…
FuseInit optimizes neural network initialization by fusing layers from deeper networks.
Sparse Transformers can approximate dense Transformers with only O(n) connections.
Neural networks are dense among Lipschitz functions with fixed Lipschitz constant.
Enhanced image denoising with MWRDCNN using residual dense blocks.
RDL-Net improves speech enhancement with fewer parameters and better performance.
Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we embrace this observation and introduce the Dense Convolutional Network (DenseNet), w…
Develops hyperparameter transfer methods for Dense Associative Memories.
Binary autoencoder with sparse hidden layer preserves information and zero reconstruction error.
Convolutional neural network (CNN) and its variants have led to many state-of-art results in various fields. However, a clear theoretical understanding about them is still lacking. Recently, multi-layer convolutional sparse coding (ML-CSC) has been proposed and proved to equal such simply stacked networks (plain networ…
As an important part of the power system, power load forecasting directly affects the national economy. The data shows that improving the load forecasting accuracy by 0.01% can save millions of dollars for the power industry. Therefore, improving the accuracy of power load forecasting has always been the pursuing goals…
New framework finds more efficient linear layers over structured matrices.
Paper hypothesizes MLP layers in LLMs can be approximated by sparse Mixture of Experts.
Image super-resolution is a challenging task and has attracted increasing attention in research and industrial communities. In this paper, we propose a novel end-to-end Attention-based DenseNet with Residual Deconvolution named as ADRD. In our ADRD, a weighted dense block, in which the current layer receives weighted f…
Recent researches have shown that deep forest ensemble achieves a considerable increase in classification accuracy compared with the general ensemble learning methods, especially when the training set is small. In this paper, we take advantage of deep forest ensemble and introduce the Dense Adaptive Cascade Forest (daF…
This paper introduces a hierarchical associative memory model with multiple layers.
Spatio-temporal (ST) data, which represent multiple time series data corresponding to different spatial locations, are ubiquitous in real-world dynamic systems, such as air quality readings. Forecasting over ST data is of great importance but challenging as it is affected by many complex factors, including spatial char…
The study finds a theoretical bound for pre-training iterations needed for pruning to yield good subnetwork performance.
We demonstrate the possibility of what we call sparse learning: accelerated training of deep neural networks that maintain sparse weights throughout training while achieving dense performance levels. We accomplish this by developing sparse momentum, an algorithm which uses exponentially smoothed gradients (momentum) to…
Inducing sparseness while training neural networks has been shown to yield models with a lower memory footprint but similar effectiveness to dense models. However, sparseness is typically induced starting from a dense model, and thus this advantage does not hold during training. We propose techniques to enforce sparsen…
In response to the development of recent efficient dense layers, this paper shows that something as simple as replacing linear components in pointwise convolutions with structured linear decompositions also produces substantial gains in the efficiency/accuracy tradeoff. Pointwise convolutions are fully connected layers…
An iterative method of learning has become a paradigm for training deep convolutional neural networks (DCNN). However, utilizing a non-iterative learning strategy can accelerate the training process of the DCNN and surprisingly such approach has been rarely explored by the deep learning (DL) community. It motivates thi…
A model of associative memory is studied, which stores and reliably retrieves many more patterns than the number of neurons in the network. We propose a simple duality between this dense associative memory and neural networks commonly used in deep learning. On the associative memory side of this duality, a family of mo…
Recently, Convolution Neural Networks (CNNs) obtained huge success in numerous vision tasks. In particular, DenseNets have demonstrated that feature reuse via dense skip connections can effectively alleviate the difficulty of training very deep networks and that reusing features generated by the initial layers in all s…
DNAS disentangles neural architecture search for better interpretability and performance.
Improved road segmentation on low-res LIDAR data for autonomous vehicles.
This paper describes our UNet based deep convolutional neural network approach on the Traffic4cast challenge 2019. Challenges task is to predict future traffic flow volume, heading and speed on high resolution whole city map. We used UNet based deep convolutional neural network to train predictive model for the short t…
Chaos in cerebellar cells enhances complexity of neural patterns.
We show that discrete synaptic weights can be efficiently used for learning in large scale neural systems, and lead to unanticipated computational performance. We focus on the representative case of learning random patterns with binary synapses in single layer networks. The standard statistical analysis shows that this…
Sparse Transformers degrade semantic information first, with early layers encoding more.
New neural network architectures use signed permutation representations for finite groups, improving performance.
We introduce a new local sparse attention layer that preserves two-dimensional geometry and locality. We show that by just replacing the dense attention layer of SAGAN with our construction, we obtain very significant FID, Inception score and pure visual improvements. FID score is improved from to on Im…
A new beta-VAE based regression model accelerates oilfield optimization studies.
New algorithm improves CRF inference and learning.
WavPool improves deep neural networks with wavelet-based pooling.
In this work, a dense recurrent convolutional neural network (DRCNN) was constructed to detect sleep disorders including arousal, apnea and hypopnea using Polysomnography (PSG) measurement channels provided in the 2018 Physionet challenge database. Our model structure is composed of multiple dense convolutional units (…
Paper perfect clusters sparse, diverse multilayer networks.
This research analyzes how input and output layers affect deep neural networks' resistance to adversarial attacks.
In this work, we investigate the value of employing deep learning for the task of wireless signal modulation recognition. Recently in [1], a framework has been introduced by generating a dataset using GNU radio that mimics the imperfections in a real wireless channel, and uses 10 different modulation types. Further, a …
New neural model processes 2D data with long-range dependencies efficiently.
TiDE uses MLP for fast, simple long-term time-series forecasting.
Does over-parameterization eliminate sub-optimal local minima for neural networks? An affirmative answer was given by a classical result in [59] for 1-hidden-layer wide neural networks. A few recent works have extended the setting to multi-layer neural networks, but none of them has proved every local minimum is global…
New method uses temperature to control sparse MoE convergence rates.
ManifoldFlow relaxes fixed-spectrum Stiefel layers to learn a positive spectrum.