Related papers: Booster: An Accelerator for Gradient Boosting Deci…

Typically, Ultra-deep neural network(UDNN) tends to yield high-quality model, but its training process is usually resource intensive and time-consuming. Modern GPU's scarce DRAM capacity is the primary bottleneck that hinders the…

Boosting as gradient descent algorithms is one popular method in machine learning. In this paper a novel Boosting-type algorithm is proposed based on restricted gradient descent with structural sparsity control whose underlying dynamics are…

The problem of adversarial robustness has been studied extensively for neural networks. However, for boosted decision trees and decision stumps there are almost no results, even though they are widely used in practice (e.g. XGBoost) due to…

Graph Neural Networks (GNNs) are becoming a promising technique in various domains due to their excellent capabilities in modeling non-Euclidean data. Although a spectrum of accelerators has been proposed to accelerate the inference of…

Projected Gradient Ascent (PGA) is the most commonly used optimization scheme in machine learning and operations research areas. Nevertheless, numerous studies and examples have shown that the PGA methods may fail to achieve the tight…

Gradient Boosting Decision Tree (GBDT) is one of the most popular machine learning models in various applications. However, in the traditional settings, all data should be simultaneously accessed in the training procedure: it does not allow…

Gradient boosting decision tree (GBDT) is an ensemble machine learning algorithm, which is widely used in industry, due to its good performance and easy interpretation. Due to the problem of data isolation and the requirement of privacy,…

Offloading compute-intensive kernels to hardware accelerators relies on the large degree of parallelism offered by these platforms. However, the effective bandwidth of the memory interface often causes a bottleneck, hindering the…

Bootstrap aggregating (Bagging) and boosting are two popular ensemble learning approaches, which combine multiple base learners to generate a composite model for more accurate and more reliable performance. They have been widely used in…

We propose two frameworks to deal with problem settings in which both structured and unstructured data are available. Structured data problems are best solved by traditional machine learning models such as boosting and tree-based…

The integration of spiking neural networks (SNNs) with transformer-based architectures has opened new opportunities for bio-inspired low-power, event-driven visual reasoning on edge devices. However, the high temporal resolution and binary…

We introduce a lightweight network to improve descriptors of keypoints within the same image. The network takes the original descriptors and the geometric properties of keypoints as the input, and uses an MLP-based self-boosting stage and a…

Score-based generative models can effectively learn the distribution of data by estimating the gradient of the distribution. Due to the multi-step denoising characteristic, researchers have recently considered combining score-based…

A novel gradient boosting framework is proposed where shallow neural networks are employed as ``weak learners''. General loss functions are considered under this unified framework with specific examples presented for classification,…

AdaBoost is an important algorithm in machine learning and is being widely used in object detection. AdaBoost works by iteratively selecting the best amongst weak classifiers, and then combines several weak classifiers to obtain a strong…

Recent works on the parallel complexity of Boosting have established strong lower bounds on the tradeoff between the number of training rounds $p$ and the total parallel work per round $t$. These works have also presented highly non-trivial…

Standard mixed-precision training of neural networks requires many bytes of accelerator memory for each model parameter. These bytes reflect not just the parameter itself, but also its gradient and one or more optimizer state variables.…

Recently, single-stage embedding based deep learning algorithms gain increasing attention in cell segmentation and tracking. Compared with the traditional "segment-then-associate" two-stage approach, a single-stage algorithm not only…

Training deep learning models can be computationally expensive. Prior works have shown that increasing the batch size can potentially lead to better overall throughput. However, the batch size is frequently limited by the accelerator memory…

This paper introduces the first low-power hardware accelerator for Spiking Transformers, an emerging alternative to traditional artificial neural networks. By modifying the base Spikformer model to use IAND instead of residual addition, the…