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.
SeReNe prunes neurons with low sensitivity to reduce network size.
TENP prunes experts and neurons in Mixture-of-Experts models for efficient deployment.
DNN pruning reduces memory footprint and computational work of DNN-based solutions to improve performance and energy-efficiency. An effective pruning scheme should be able to systematically remove connections and/or neurons that are unnecessary or redundant, reducing the DNN size without any loss in accuracy. In this p…
Unseen or out-of-domain data can seriously degrade the performance of a neural network model, indicating the model's failure to generalize to unseen data. Neural net pruning can not only help to reduce a model's size but can improve the model's generalization capacity as well. Pruning approaches look for low-salient ne…
Recurrent neural networks (RNNs) have recently achieved remarkable successes in a number of applications. However, the huge sizes and computational burden of these models make it difficult for their deployment on edge devices. A practically effective approach is to reduce the overall storage and computation costs of RN…
OPNP prunes parameters and neurons to improve OOD detection without training.
We introduce Delay Pruning, a simple yet powerful technique to regularize dynamic Boltzmann machines (DyBM). The recently introduced DyBM provides a particularly structured Boltzmann machine, as a generative model of a multi-dimensional time-series. This Boltzmann machine can have infinitely many layers of units but al…
Partial fusion combines neural networks to balance accuracy and efficiency.
Survey on pruning CNN models to reduce size for edge devices.
Binary Stochastic Filtering (BSF), the algorithm for feature selection and neuron pruning is proposed in this work. The method defines filtering layer which penalizes amount of the information involved in the training process. This information could be the input data or output of the previous layer, which directly lead…
Greedy selection finds smaller, more accurate subnetworks.
New Lipschitz bound for ReLU networks resists weight rescaling.
Network pruning is aimed at imposing sparsity in a neural network architecture by increasing the portion of zero-valued weights for reducing its size regarding energy-efficiency consideration and increasing evaluation speed. In most of the conducted research efforts, the sparsity is enforced for network pruning without…
We introduce Continual Learning via Neural Pruning (CLNP), a new method aimed at lifelong learning in fixed capacity models based on neuronal model sparsification. In this method, subsequent tasks are trained using the inactive neurons and filters of the sparsified network and cause zero deterioration to the performanc…
Data-independent pruning method reduces neural network size with accuracy guarantees.
Theoretical framework for neural network compression using sparsity norms.
We introduce a mixed integer program (MIP) for assigning importance scores to each neuron in deep neural network architectures which is guided by the impact of their simultaneous pruning on the main learning task of the network. By carefully devising the objective function of the MIP, we drive the solver to minimize th…
Recent advances in the sparse neural network literature have made it possible to prune many large feed forward and convolutional networks with only a small quantity of data. Yet, these same techniques often falter when applied to the problem of recovering sparse recurrent networks. These failures are quantitative: when…
With the rapid scaling up of deep neural networks (DNNs), extensive research studies on network model compression such as weight pruning have been performed for improving deployment efficiency. This work aims to advance the compression beyond the weights to neuron activations. We propose the joint regularization techni…
Simple iterative method reduces deep network size significantly.
This paper finds a new way to compress CNN weights, improving on pruning and quantization.
Neural network pruning reduces the computational cost of an over-parameterized network to improve its efficiency. Popular methods vary from -norm sparsification to Neural Architecture Search (NAS). In this work, we propose a novel pruning method that optimizes the final accuracy of the pruned network and distil…
Dirichlet pruning compresses neural networks by removing unimportant units.
i-SpaSP prunes neural networks by identifying important groups of parameters, improving pruning efficiency.
As neural networks become widely deployed in different applications and on different hardware, it has become increasingly important to optimize inference time and model size along with model accuracy. Most current techniques optimize model size, model accuracy and inference time in different stages, resulting in subopt…
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…
BMRS offers a Bayesian approach to structured pruning of neural networks.
While state-of-the-art NLP explainability (XAI) methods focus on explaining per-sample decisions in supervised end or probing tasks, this is insufficient to explain and quantify model knowledge transfer during (un-)supervised training. Thus, for TX-Ray, we modify the established computer vision explainability principle…
Logarithmic pruning simplifies lottery ticket hypothesis.
New learning algorithm mimics biological neural networks.
Structural pruning of neural network parameters reduces computation, energy, and memory transfer costs during inference. We propose a novel method that estimates the contribution of a neuron (filter) to the final loss and iteratively removes those with smaller scores. We describe two variations of our method using the …
Recently, in the paper "Weight Agnostic Neural Networks" Gaier & Ha utilized architecture search to find networks where the topology completely encodes the knowledge. However, architecture search in topology space is expensive. We use the existing framework of binarized networks to find performant topologies by constra…
New SDP method certifies neural network robustness across all classes efficiently.
Paper proposes neural network for efficient MIMO channel estimation and pilot reduction.
Previous work showed empirically that large neural networks can be significantly reduced in size while preserving their accuracy. Model compression became a central research topic, as it is crucial for deployment of neural networks on devices with limited computational and memory resources. The majority of the compress…
Improves parallel deep model performance by restructuring and pruning.
Neural plasticity is an important functionality of human brain, in which number of neurons and synapses can shrink or expand in response to stimuli throughout the span of life. We model this dynamic learning process as an -norm regularized binary optimization problem, in which each unit of a neural network (e.g., …
Sparser Random Feature Models via IMP (ShRIMP) efficiently learns sparse models for high-dimensional data.
The study examines if ReLU activation function is optimal for modularity in neural networks.
A new method identifies a stable subnetwork in overparameterized student models.
Dropout-based regularization methods can be regarded as injecting random noise with pre-defined magnitude to different parts of the neural network during training. It was recently shown that Bayesian dropout procedure not only improves generalization but also leads to extremely sparse neural architectures by automatica…
Recent pruning methods at initialization fall short of random pruning's accuracy.
ICE-Pruning accelerates deep neural network pruning by 9.61x.
DSA efficiently allocates sparsity across layers for budgeted pruning.
Magnitude-based pruning is one of the simplest methods for pruning neural networks. Despite its simplicity, magnitude-based pruning and its variants demonstrated remarkable performances for pruning modern architectures. Based on the observation that magnitude-based pruning indeed minimizes the Frobenius distortion of a…
Pruning neural network parameters is often viewed as a means to compress models, but pruning has also been motivated by the desire to prevent overfitting. This motivation is particularly relevant given the perhaps surprising observation that a wide variety of pruning approaches increase test accuracy despite sometimes …
Dynamic pruning during training reduces deep network complexity without significant accuracy loss.
Expanding neural networks improves their learning from noisy data.