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.
Optimizes wide low-rank neural networks for reduced parameters and cost.
FLAML automates model selection and hyperparameter tuning with low resource cost.
MUMBO optimizes multiple tasks efficiently, even with low-cost related functions.
The multimodal web elements such as text and images are associated with inherent memory costs to store and transfer over the Internet. With the limited network connectivity in developing countries, webpage rendering gets delayed in the presence of high-memory demanding elements such as images (relative to text). To ove…
Label tree-based algorithms are widely used to tackle multi-class and multi-label problems with a large number of labels. We focus on a particular subclass of these algorithms that use probabilistic classifiers in the tree nodes. Examples of such algorithms are hierarchical softmax (HSM), designed for multi-class class…
In this work, a new approach for Sun tracking systems is presented. Due to the current system limitations regarding costs and operational problems, a new approach based on low cost, computer vision open hardware and deep learning has been developed. The preliminary tests carried out successfully in Plataforma solar de …
Sparse nearest-centroid classifiers detect relevant features for classification.
Researchers develop neural optimal transport with Lagrangian costs for efficient computation.
Low rank tensor learning, such as tensor completion and multilinear multitask learning, has received much attention in recent years. In this paper, we propose higher order matching pursuit for low rank tensor learning problems with a convex or a nonconvex cost function, which is a generalization of the matching pursuit…
Solving symmetric positive definite linear problems is a fundamental computational task in machine learning. The exact solution, famously, is cubicly expensive in the size of the matrix. To alleviate this problem, several linear-time approximations, such as spectral and inducing-point methods, have been suggested and a…
New method reduces computational cost for nonnegative low rank matrix approximation.
New GPnn method achieves scalable regression with low computational cost.
New framework reduces cost of financial option pricing simulations on FPGAs.
A new method reduces inference cost for FwFM by allowing it to scale with item fields only.
Low-rank modeling plays a pivotal role in signal processing and machine learning, with applications ranging from collaborative filtering, video surveillance, medical imaging, to dimensionality reduction and adaptive filtering. Many modern high-dimensional data and interactions thereof can be modeled as lying approximat…
Low-cost sensors improve air quality prediction accuracy significantly.
New method detects if data points were used in training models with low cost and high power.
StatQAT optimizes quantization for deep networks, reducing computational cost and memory usage.
Recurrent neural networks are a powerful tool, but they are very sensitive to their hyper-parameter configuration. Moreover, training properly a recurrent neural network is a tough task, therefore selecting an appropriate configuration is critical. Varied strategies have been proposed to tackle this issue. However, mos…
We study the approximate nearest neighbour method for cost-sensitive classification on low-dimensional manifolds embedded within a high-dimensional feature space. We determine the minimax learning rates for distributions on a smooth manifold, in a cost-sensitive setting. This generalises a classic result of Audibert an…
oPoW proposes a new PoW algorithm to reduce mining costs and environmental impact.
The usability and practicality of any machine learning (ML) applications are largely influenced by two critical but hard-to-attain factors: low latency and low cost. Unfortunately, achieving low latency and low cost is very challenging when ML depends on real-world data that are highly distributed and rapidly growing (…
Implementing large-scale deep neural networks with high computational complexity on low-cost IoT devices may inevitably be constrained by limited computation resource, making the devices hard to respond in real-time. This disjunction makes the state-of-art deep learning algorithms, i.e. CNN (Convolutional Neural Networ…
ROAD-EnKFs use learned low-dimensional models to improve state reconstruction and forecasting.
A new parallel algorithm for learning optimal policies in MDPs with low communication costs.
A deep learning algorithm designs low-cost SPP films.
This work introduces a novel nonparametric density index defined on graphs, the Sum-over-Forests (SoF) density index. It is based on a clear and intuitive idea: high-density regions in a graph are characterized by the fact that they contain a large amount of low-cost trees with high outdegrees while low-density regions…
ECM uses class means for efficient early exits in neural networks.
Kernel matrices (e.g. Gram or similarity matrices) are essential for many state-of-the-art approaches to classification, clustering, and dimensionality reduction. For large datasets, the cost of forming and factoring such kernel matrices becomes intractable. To address this challenge, we introduce a new adaptive sampli…
New method quantizes neural networks for mobile devices.
This work reduces computation cost for on-device CNN training.
This paper focuses on projection-free methods for solving smooth Online Convex Optimization (OCO) problems. Existing projection-free methods either achieve suboptimal regret bounds or have high per-iteration computational costs. To fill this gap, two efficient projection-free online methods called ORGFW and MORGFW are …
This letter proposes a low-computational Bayesian algorithm for noisy sparse recovery in the context of one bit compressed sensing with sensing matrix perturbation. The proposed algorithm which is called BHT-MLE comprises a sparse support detector and an amplitude estimator. The support detector utilizes Bayesian hypot…
Faster GW alignment for incomparable point clouds via low-rank couplings.
The successive projection algorithm (SPA) can quickly solve a nonnegative matrix factorization problem under a separability assumption. Even if noise is added to the problem, SPA is robust as long as the perturbations caused by the noise are small. In particular, robustness against noise should be high when handling th…
Unified framework reduces NFEs for inverse problems.
This paper develops a method to train compact neural networks with reduced memory and computational costs.
New algorithm improves deep learning models' robustness without sacrificing accuracy.
Study assesses CNN model robustness to noise in low-cost CT scans.
Using Intel's Loihi neuromorphic research chip and ABR's Nengo Deep Learning toolkit, we analyze the inference speed, dynamic power consumption, and energy cost per inference of a two-layer neural network keyword spotter trained to recognize a single phrase. We perform comparative analyses of this keyword spotter runni…
Researchers develop methods to reduce simulation costs for cardiovascular modeling.
CNNs show sensitivity to low-frequency signals due to image frequency distribution.
New method improves model explainability and accuracy with low computational cost.
Paper presents a low-cost algorithm for bipartite ranking with improved sample size requirements.
Optimizes optimal transport distances using low-dimensional embeddings.
Improved machine learning with reduced tensor rank constraints and dropout.
Low-precision training reduces computational cost and produces efficient models. Recent research in developing new low-precision training algorithms often relies on simulation to empirically evaluate the statistical effects of quantization while avoiding the substantial overhead of building specific hardware. To suppor…
A new BO framework reduces costs by using low-fidelity data.