arXiv research

Multi-model FL improves performance without sharing data.

Paper improves gender detection on social media using deep learning.

We identify a phenomenon, which we refer to as multi-model forgetting, that occurs when sequentially training multiple deep networks with partially-shared parameters; the performance of previously-trained models degrades as one optimizes a subsequent one, due to the overwriting of shared parameters. To overcome this, w…

GANs improve stochastic dynamics prediction by selecting randomly between models.

CoSMIC extends flow-based SVI to transdimensional problems.

This paper improves model fusion by training-time neuron alignment, reducing barriers in multi-model fusion.

NetFuse merges different DNN models with varying weights for faster inference.

With the increasing penetration of solar power into power systems, forecasting becomes critical in power system operations. In this paper, an hourly-similarity (HS) based method is developed for 1-hour-ahead (1HA) global horizontal irradiance (GHI) forecasting. This developed method utilizes diurnal patterns, statistic…

Solar forecasting accuracy is affected by weather conditions, and weather awareness forecasting models are expected to improve the performance. However, it may not be available and reliable to classify different forecasting tasks by using only meteorological weather categorization. In this paper, an unsupervised cluste…

NN-GPR improves climate model predictions by preserving fine-scale spatial information.

Federated survival analysis outperforms local and centralized training, with RSF offering the best balance of discrimination, calibration, and robustness.

Traditional nearest points methods use all the samples in an image set to construct a single convex or affine hull model for classification. However, strong artificial features and noisy data may be generated from combinations of training samples when significant intra-class variations and/or noise occur in the image s…

This paper proposes a novel approach to train deep neural networks by unlocking the layer-wise dependency of backpropagation training. The approach employs additional modules called local critic networks besides the main network model to be trained, which are used to obtain error gradients without complete feedforward …

Energy price forecasting is a relevant yet hard task in the field of multi-step time series forecasting. In this paper we compare a well-known and established method, ARMA with exogenous variables with a relatively new technique Gradient Boosting Regression. The method was tested on data from Global Energy Forecasting …

Machine Learning models are often composed of pipelines of transformations. While this design allows to efficiently execute single model components at training time, prediction serving has different requirements such as low latency, high throughput and graceful performance degradation under heavy load. Current predicti…

FlexServe simplifies deployment of PyTorch models as REST endpoints.

The paper explores MMPR to select diverse models for scientific insight.

Visual system compares and evaluates machine learning models for clinical data predictions.

A growing interest has been witnessed recently from both academia and industry in building nearest neighbor search (NNS) solutions on top of full-text search engines. Compared with other NNS systems, such solutions are capable of effectively reducing main memory consumption, coherently supporting multi-model search and…

Unified framework connects different neural network models.

New algorithms reduce bias in federated learning for non-i.i.d. data.

Despite being popularly used in many applications, neural network models have been found to be vulnerable to adversarial examples, i.e., carefully crafted examples aiming to mislead machine learning models. Adversarial examples can pose potential risks on safety and security critical applications. However, existing def…

In recent years, machine learning has developed rapidly, enabling the development of applications with high levels of recognition accuracy relating to the use of speech and images. However, other types of data to which these models can be applied have not yet been explored as thoroughly. Labelling is an indispensable s…

Study examines remittances in Nepal, linking external demand and domestic monetary conditions.

New algorithm reduces sample complexity for online reinforcement learning.

PBC improves AI and dynamical subseasonal forecasts by reducing biases.

FinTradeBench benchmarks LLMs for financial reasoning combining company fundamentals and market signals.

R-PLS improves analysis of brain functional connectivity matrices.

Generative AI models enhance sector-based investment portfolios, but performance varies by market conditions.

Study improves document processing in banking with multimodal analytics.

Seasonal influenza infects between 10 and 50 million people in the United States every year, overburdening hospitals during weeks of peak incidence. Named by the CDC as an important tool to fight the damaging effects of these epidemics, accurate forecasts of influenza and influenza-like illness (ILI) forewarn public he…

Research capacity is critical in understanding systemic risk and informing new regulation. Banking regulation has not kept pace with all the complexities of financial innovation. The academic literature on systemic risk is rapidly expanding. The majority of papers analyse a single source or a consolidated source of ris…

Foundation models improve on econometric benchmarks for forecasting volatility, but vary widely across models.

CLQT benchmarks LLM portfolio managers by evaluating their decision-making process, not just returns.