Multi-model FL improves performance without sharing data.
problem Training multiple models in a federated setting without data sharing.
method Proposed two variants of FedAvg for multi-model FL with provable convergence guarantees.
result Multi-model FL can have better performance than training each model separately.
A new solar forecasting method uses clustering and machine learning to improve accuracy.
problem Improving solar forecasting accuracy through weather conditions.
method Unsupervised clustering, pattern recognition, and multi-model machine learning.
result UC-based models outperform non-UC models by approximately 20%.
PRETZEL optimizes machine learning prediction serving systems for better performance.
problem Low latency, high throughput, and graceful performance degradation under heavy load in prediction serving systems.
method Introducing a novel white box architecture enabling both end-to-end and multi-model optimizations.
result Average 5.5x reduction in 99th percentile latency, 25x reduction in memory footprint, and 4.7x increase in throughput compared to state-of-the-art approaches.
GANs improve stochastic dynamics prediction by selecting randomly between models.
problem Accurately generating stochastic dynamics from multi-model GANs.
method Applying GANs to a lattice stochastic process, adding noise, and selecting randomly between models.
result Multi-model approach leads to significant improvement in accuracy of stochastic dynamics prediction.
Improved solar forecasting using hourly-similarity based method.
problem Critical need for accurate hourly solar forecasting in power systems.
method Developed an HS-based method using diurnal patterns and statistical distinctions.
result HS-based method significantly outperforms non-HS method in forecasting accuracy.
Multi-model forgetting occurs when training multiple deep networks sequentially, leading to performance degradation of previously trained models.
problem Performance degradation of previously trained models when sequentially training multiple deep networks with shared parameters.
method Introduce a weight plasticity loss that regularizes the learning of shared parameters based on their importance for previous models.
result Weight plasticity loss effectively preserves the performance of previously trained models during sequential training and neural architecture search.
Paper improves gender detection on social media using deep learning.
problem Traditional classifiers struggle with social media data volume.
method Ensemble deep learning with multi-model architectures.
result Improved gender detection accuracy on social media posts.
NetFuse merges different DNN models with varying weights for faster inference.
problem Inference speed of DNN models with different weights cannot be improved using existing techniques.
method NetFuse merges models with the same architecture but different weights and inputs, replacing operations with more general ones.
result NetFuse can speed up DNN inference time up to 3.6x on a NVIDIA V100 GPU.
Visual system compares and evaluates machine learning models for clinical data predictions.
problem Challenges in comparing and evaluating different machine learning models for medical predictions.
method Developed a visual analytics system to compare and evaluate multiple models' prediction criteria and consistency.
result Demonstrated the effectiveness of the visual analytics system in assisting clinicians and researchers.
This paper improves model fusion by training-time neuron alignment, reducing barriers in multi-model fusion.
problem Diverse neuron permutations across different settings hinder model fusion performances.
method Training-time neuron alignment using fixed neuron anchors to reduce training-time permutations.
result Training-time neuron alignment improves fusion of pretrained models and federated learning performances.
CoSMIC extends flow-based SVI to transdimensional problems.
problem Bayesian structure learning and model selection with multi-model parameter spaces.
method Normalizing flows with a combined stochastic variational transdimensional inference approach.
result Improved performance on high-cardinality model spaces.
FlexServe simplifies deployment of PyTorch models as REST endpoints.
problem Lack of control over model evolution and strict security requirements in operational environments.
method Developed FlexServe, a library to deploy multi-model ensembles with flexible batching.
result Rapid deployment of PyTorch models without intermediate transformations.
Federated survival analysis outperforms local and centralized training, with RSF offering the best balance of discrimination, calibration, and robustness.
problem Survival analysis models require large, diverse cohorts but are limited by privacy regulations and lack of centralized data.
method Federated learning (FL) is used to train shared models without exchanging raw data.
result FL consistently outperforms local training and approaches, and occasionally exceeds centralized performance.
Paper introduces new techniques for real-time sensor data labelling.
problem Challenges in real-time sensor data labelling, especially with machine learning models.
method Developed new techniques for labelling at the point of collection.
result Improved accuracy of machine learning models through real-time labelling.
PBC improves AI and dynamical subseasonal forecasts by reducing biases.
problem Subseasonal forecast accuracy drops due to model biases and compounding errors.
method Probabilistic bias correction (PBC) using machine learning to correct historical forecasts.
result PBC doubles AI Forecasting System's subseasonal skill and improves dynamical model skill.
A new method trains deep neural networks using local critic networks.
problem Training deep neural networks efficiently and effectively.
method Employing local critic networks for error gradient calculation and cascaded learning.
result The approach improves training efficiency and performance of deep neural networks.
NN-GPR improves climate model predictions by preserving fine-scale spatial information.
problem Dilution of fine-scale spatial information and bias in model averaging.
method Gaussian process regression with an infinitely wide deep neural network.
result NN-GPR produces more accurate and detailed climate projections.
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…
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 …
Study examines remittances in Nepal, linking external demand and domestic monetary conditions.
problem Understanding the dynamics of remittances in Nepal's economy.
method Constructed composite indices via PCA for external demand and domestic monetary conditions. Used ARDL, cointegration, DOLS, ECM, and machine learning for analysis.
result Strong positive long-run effect of external demand on remittances, significant negative impact of tighter domestic monetary conditions.
MulDef defends neural networks against adversarial examples by combining multiple models.
problem Vulnerability of neural networks to adversarial examples.
method A general defense framework based on multiple models with robustness diversity.
result Substantially improved accuracy on adversarial examples (22-74%) while maintaining similar accuracy on legitimate examples.
The paper explores MMPR to select diverse models for scientific insight.
problem Model selection often fails to bring multiple underlying patterns to light.
method Multi-model penalized regression (MMPR) to acknowledge model uncertainty.
result Different penalty settings can promote either shrinkage or sparsity of coefficients in separate models.
New algorithms reduce bias in federated learning for non-i.i.d. data.
problem Client and block biases in federated learning with non-i.i.d. data.
method Multi-model parallel SGD (MM-PSGD) and multi-chain parallel SGD (MC-PSGD) algorithms.
result Achieve a linear speedup with convergence rate O ( 1 / N T ) O(1/\sqrt{NT}) O ( 1/ N T ) . New algorithm reduces sample complexity for online reinforcement learning.
problem Reducing sample complexity for online reinforcement learning in nonlinear systems.
method Generalized algorithm for various dynamical systems, including neural networks.
result Achieves policy regret of O(Nε^2 + d_u ln(m(ε))/ε^2) in general settings.
Unified framework connects different neural network models.
problem Understanding the geometry of neural network loss landscapes.
method Unified framework capturing four symmetry classes.
result First discovery of low- and zero-barrier linear interpolation paths.
Paper improves full-text search engines for fast exact NNS in binary codes.
problem Efficient nearest neighbor search in Hamming space for full-text search engines.
method Revisits and combines three techniques from information retrieval: bit operation, subs-code filtering, and data preprocessing with permutation.
result Significant speed-ups for NNS in binary codes over state-of-the-art term match approach.
Adaptive ensemble improves flu forecasts with minimal data.
problem Accurate flu forecasts to help public health.
method Adaptive stacking of ensembles, changing model weights weekly.
result Adaptive ensemble outperforms static ensembles in flu forecasts.
FinTradeBench benchmarks LLMs for financial reasoning combining company fundamentals and market signals.
problem Challenges in evaluating financial reasoning models for LLMs.
method Developed a benchmark integrating company fundamentals and trading signals, using a calibration-then-scaling framework.
result Clear performance gap between LLMs, retrieval improves reasoning over textual fundamentals but not trading signals.
R-PLS improves analysis of brain functional connectivity matrices.
problem Improving analysis of functional connectivity matrices in brain imaging.
method Introducing R-PLS, a generalization of PLS for symmetric positive definite matrices.
result R-PLS identifies key functional connections in brain imaging datasets.
Generative AI models enhance sector-based investment portfolios, but performance varies by market conditions.
problem Improving investment performance through better stock selection in volatile markets.
method Applied LLMs from OpenAI, Google, Anthropic, DeepSeek, and xAI to select and weight stocks within S&P 500 sectors.
result LLM-weighted portfolios outperform sector indices in stable markets but underperform in volatile ones.
Study improves document processing in banking with multimodal analytics.
problem Raising operational efficiency in banking through document-intensive processes.
method Comparative analysis of text classifiers and multimodal model (LayoutXLM) on company register extracts.
result Incorporating layout information in a model substantially increases performance.
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.
problem Comparing pretrained time series foundation models to econometric benchmarks for volatility forecasting.
method Systematic comparison of nine zero-shot TSFMs against eight econometric specifications on 50 assets across 3 markets and 3 horizons.
result Tiny Time Mixers (TTM) is the only model that consistently beats the Log-HAR benchmark, but performance varies widely across models.
Machine teaching aims to democratize machine learning by making it easier for non-experts to teach machines.
problem Current machine learning systems require specialized knowledge, limiting their creation and use.
method Focus on making teaching machines accessible and easy, emphasizing teacher interaction and design principles.
result By decoupling knowledge about machine learning algorithms from teaching, innovation can accelerate and empower new uses.
The paper reviews machine learning safety techniques for autonomous vehicles.
problem Challenges in machine learning safety for autonomous vehicles.
method Organizes practical safety techniques to complement engineering safety.
result Enhances dependability and safety of machine learning algorithms in autonomous vehicles.
This paper surveys optimization methods in machine learning.
problem Challenges in optimization methods due to growing data and model complexity.
method Systematic review of optimization methods from machine learning perspective.
result Guidance for optimization and machine learning research.
Optimal control theory applied to machine learning adversarial attacks.
problem Adversarial machine learning threats and detection challenges.
method Optimal control theory applied to machine learning systems.
result Advances in control theory and reinforcement learning can enhance adversarial machine learning research.
Optimization techniques for machine learning explained.
problem Improving machine learning models' performance.
method Course notes and tutorials on optimization methods.
result Comprehensive coverage of optimization techniques.
Machine learning aids in clinical prediction tasks.
problem Improving accuracy in clinical predictions.
method Introduction to machine learning concepts and algorithms, followed by practical application to clinical datasets.
result Demonstrated the application of machine learning models to clinical prediction problems.
CLQT benchmarks LLM portfolio managers by evaluating their decision-making process, not just returns.
problem Most benchmarks rank LLMs by returns, ignoring their decision-making process and potential for look-ahead leakage.
method CLQT reframes evaluation as diagnosis, using a closed-loop, cost-aware, strategy-consistent environment with a five-stage cycle.
result CLQT provides a durable map of agent competencies and limitations, separating outcome from process.
Study compares cloud ML services for binary classification tasks.
problem Evaluate performance of major cloud ML services on binary classification.
method Constructed benchmark using Kaggle datasets; compared Azure and Amazon services.
result Identifies strengths and weaknesses of current cloud ML services.
This paper surveys informed machine learning, integrating prior knowledge into ML.
problem Machine learning's limitations with insufficient data.
method Taxonomy and survey of informed machine learning approaches.
result A taxonomy classifies informed machine learning approaches based on knowledge source, representation, and integration.
Survey on techniques to make machine learning models understandable.
problem Humans cannot understand complex machine learning model decisions.
method Survey of existing techniques to increase interpretability.
result Challenges and achievements in interpretable machine learning need further exploration.
Optimal Transport enhances machine learning with new methods.
problem Comparing and manipulating probability distributions in machine learning.
method Probabilistic framework rooted in rich history and theory.
result New solutions in generative modeling and transfer learning.
Automated machine learning simplifies model selection and tuning.
problem Manual tuning of machine learning models by data scientists is time-consuming and requires extensive expertise.
method Review of AutoML techniques including automated feature engineering, model learning, and deep learning.
result Current AutoML techniques can significantly reduce the burden of manual tuning.
Market incentivizes parties to share high-quality data for collaborative machine learning tasks.
problem Fair revenue distribution and data replication threats in collaborative machine learning markets.
method Introduces a novel payment division function robust to replication and customized output models.
result Validated assumptions and showed approximate satisfaction for commonly used models.
DoubleML implements machine learning for causal inference in R.
problem Estimating causal effects in regression models with high-dimensional data.
method Double machine learning framework with Neyman orthogonality and sample splitting.
result Valid inference on causal parameters using machine learning methods.
Quantum computers can speed up machine learning optimization problems.
problem Long computation times and high resource requirements for classical optimization algorithms in machine learning.
method Developed a mathematical model to leverage quantum parallelism for machine learning.
result Quantum machine learning applied to a 3D time-varying image demonstrated significant speedup.