Quantized deep neural networks (QDNNs) are attractive due to their much lower memory storage and faster inference speed than their regular full precision counterparts. To maintain the same performance level especially at low bit-widths, QDNNs must be retrained. Their training involves piecewise constant activation func…
On-device research index
arXiv research
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.
169,051 papers · 148 categories
Trend · papers per month
48 results for “gradient blending”
The paper proposes blending gradient boosted trees and neural networks for hierarchical time series forecasting.
problem Point and probabilistic forecasting of hierarchical time series.
method A blending methodology of gradient boosted trees and neural networks, with feature engineering and diverse model selection.
result Ranked within the gold medal range in both Accuracy and Uncertainty tracks of the M5 Competition.
A new method quantizes neural networks to low-precision without STE, improving accuracy.
problem Quantization of neural networks to low-precision without a complete theoretical understanding.
method Alpha-blending (AB) using stochastic gradient descent (SGD) to quantize weights and gradually increase the coefficient .
result Improves top-1 accuracy by 0.9% on 1-bit BinaryNet, 0.82% on 8-bit MobileNet v1, and 2.93% on 4-bit ResNet_50 v1/2 compared to STE.
Blended Matching Pursuitmath.OC
New algorithm combines gradient and coordinate descent steps for faster convergence.
problem Optimizing smooth convex functions over atom-spans.
method Blended matching pursuit combining coordinate descent and gradient descent.
result Derives linear convergence rates for non-strongly convex functions.
Improves deep learning models by blending gradients from training loss and auxiliary objective.
problem Minimizing a single training loss while encouraging desirable model properties.
method Solves a bilevel optimization problem by combining training loss gradients and orthogonal projections of auxiliary gradients.
result Bloop method leads to better performance than other gradient surgery methods without EMA.
New algorithm completes nonnegative tensors with fewer samples and faster convergence.
problem Tensor completion tension between sample complexity and computational complexity.
method Integer programming and Blended Conditional Gradients algorithm.
result Achieves information-theoretic sample complexity rate with practical convergence.
Study shows E2E training fails for over-parameterized models.
problem When does E2E training fail for complex Deep Network architectures?
method Blend gradient between independent training and E2E training.
result Optimum can lie between ensemble and E2E, challenging traditional approaches.
Deformations of a Courant Algebroid E and its Dirac subbundle A have been widely considered under the assumption that the pseudo-Euclidean metric is fixed. In this paper, we attack the same problem in a setting that allows the pseudo-Euclidean metric to deform. Thanks to Roytenberg, a Courant algebroid is equivalent to…
Reducing overestimating and underestimating volatility via the augmented blending-ARCH modelq-fin.ST
New model improves volatility forecasting by reducing overestimation and underestimation.
problem SVR-GARCH model overestimates or underestimates volatility, hindering peak or trough behaviors.
method Proposes blending ARCH and augmented blending-ARCH models to improve volatility forecasting.
result Empirical results show improved volatility forecasting ability.
New algorithm improves source separation with multi-trial supervision.
problem Non-convex optimization and interpretability of independent components.
method Proximal gradient-type algorithm in invertible matrices with backpropagation for joint learning.
result Increased success rate of non-convex optimization and improved interpretability.
Study shows ethanol blends and incentives can significantly reduce transportation carbon emissions.
problem Rapid growth in electric vehicles requires complementary strategies to decarbonize transportation.
method Analysis of ethanol blending, regulatory incentives, and economic assessments.
result Ethanol blending, especially E15 and E85, can substantially reduce carbon emissions and provide economic benefits.
BayesBlend blends multiple models' predictions for better insurance loss predictions.
problem Improving insurance loss predictions by combining multiple models.
method Pseudo-Bayesian model averaging, stacking, and hierarchical stacking.
result BayesBlend provides a user-friendly way to blend model predictions and estimate weights.
Formalizes explanations as blending input and model output.
problem Creating clear and consistent explanations for model predictions.
method Defines properties of explanation functions and links them to model layers.
result Consistency of activations across layers implies consistency of explanations.
Quantum walks blend patterns into splines when averaged.
problem Understanding the asymptotic patterns of quantum random walks.
method Averaging over quantum coins using the Haar measure.
result Patterns blend into splines, showing a unified behavior.
This paper improves level generation using VAEs for coherent, logically following segments.
problem Generating coherent levels of non-fixed length and blending levels from different games.
method Sequential segment-based level generation using VAEs with a classifier for logical placement.
result Generated levels are more coherent and capable of blending levels from different games.
Study evaluates predictive models for blended courses, analyzing performance across different offerings.
problem Limited success in predicting student performance in blended courses.
method Used data from two offerings of two different undergraduate courses to train and evaluate models.
result Models perform better on the same offering and less well on different offerings of the same course.
New PCGML approach generates novel game content across multiple platformer domains.
problem Generating novel game content in new domains.
method Using a new affordance and path vocabulary, variational autoencoders trained on data from six platformer games produce new content with varying proportions of different domains.
result Captures latent level space spanning multiple domains and generates new content with varying proportions of different domains.
Quantum kernel improves probabilistic time series forecasting.
problem Quantifying uncertainty in probabilistic time series predictions.
method Integrates quantum kernel with Gaussian process regression.
result Quantum kernel enhances forecasting performance.
The paper presents a framework for optimizing crypto-currency portfolios using generative models.
problem Optimizing crypto-currency portfolios using generative models.
method The approach involves evaluating diverse pairings of generative model forecasts and objective functions, using simulations and blending strategies.
result Eclectic blended portfolios outperform individual generative model-based portfolios.
Generative model blends query input with latent states for structured improvisation.
problem Generating structured music from latent states of a neural network.
method Used a Variational Autoencoder (VAE) trained on a specific style corpus, and controlled blending with a noisy channel.
result Generated music with longer-term structure that blends query input with network style.
Proposes glocal hypergradient estimation for hyperparameter optimization.
problem Combining reliability and efficiency in hyperparameter optimization.
method Uses Koopman operator theory to approximate global hypergradients from local ones.
result Achieves both reliability and efficiency in hyperparameter optimization.
In the NIPS 2017 Learning to Run challenge, participants were tasked with building a controller for a musculoskeletal model to make it run as fast as possible through an obstacle course. Top participants were invited to describe their algorithms. In this work, we present eight solutions that used deep reinforcement lea…
A novel approach for augmenting histopathological images by blending Gaussian-Laplacian pyramids.
problem Data imbalance and inter-patient variability in histopathological images.
method Image blending using Gaussian-Laplacian pyramids to distribute inter-patient variability.
result Promising gains in performance compared to existing data augmentation techniques.
Study examines Indian equity mutual funds' investment style and risk-shifting.
problem Understanding how Indian equity mutual funds' investment styles affect their returns.
method Estimating size and style beta coefficients, identifying breakpoints, analyzing investment styles, and assessing risk-shifting intensity.
result Funds can enhance returns by shifting to high-return styles like Small Value and Small Blend.
A new framework for training structured prediction models using smoothing.
problem Training smooth structured prediction models with non-smooth objectives.
method Smoothing over the maximum margin structured prediction objective to enable fast optimization.
result The proposed framework enables the use of efficient optimization algorithms for structured prediction.
OPERA blends multiple OPE estimators to evaluate new policies offline.
problem Lack of reliable offline policy evaluation methods for new policies.
method Adaptive blending of multiple OPE estimators without explicit selection.
result Consistent and reliable policy evaluation framework for offline RL.
AMEAN tackles BTDA by learning meta-sub-targets to bridge domain gaps and misalignments.
problem Blending-target Domain Adaptation (BTDA) with multiple sub-targets that are hard to distinguish.
method AMEAN uses two adversarial processes: first to align source and mixed target domains, second to learn meta-sub-targets.
result AMEAN significantly outperforms existing DA algorithms in BTDA scenarios.
This study introduces a new GAS blending ensemble model for Bitcoin price prediction.
problem Predicting Bitcoin price fluctuations in the cryptocurrency market.
method Integrates advanced ensemble learning methods, feature selection algorithms, and sentiment analysis.
result The GAS model demonstrates excellent performance in daily Bitcoin trend prediction.
Breiman's two cultures reconciled through blending statistical thinking.
problem Tension between parametric statistical and machine learning approaches.
method Establishing a link between parametric statistical and machine learning frameworks.
result Integrated statistical thinking can bridge the gap between two cultures.
Improved prediction of polymer morphology through machine learning and simulations.
problem Understanding and predicting the morphology of multi-component polymer blends.
method Modified Cahn-Hilliard model for simulations, machine learning for clustering and prediction.
result Machine learning achieved 90% accuracy in predicting polymer morphology.
PTOPOFL uses topological descriptors to protect privacy in federated learning.
problem Privacy and data reconstruction attacks in federated learning.
method PTOPOFL replaces gradient communication with persistent homology feature vectors for privacy and topology-guided aggregation.
result PTOPOFL achieves higher AUC and reduces reconstruction risk compared to gradient sharing.
We introduce a new framework for training deep generative models for high-dimensional conditional density estimation. The Bottleneck Conditional Density Estimator (BCDE) is a variant of the conditional variational autoencoder (CVAE) that employs layer(s) of stochastic variables as the bottleneck between the input a…
Neural GDEs improve graph prediction by blending discrete structures and differential equations.
problem Dynamic graph prediction challenges in irregularly sampled data.
method Continuous-depth graph neural networks (GNNs) with Neural GDEs.
result Neural GDEs enhance performance across various applications.
Blend-ASC improves self-consistency efficiency by dynamically allocating samples, reducing costs.
problem Efficiently applying self-consistency to large datasets is computationally expensive.
method Blend-ASC dynamically allocates samples during inference, improving efficiency.
result Blend-ASC reduces sample usage by 6.8x on average compared to vanilla self-consistency.
BiPE blends intra-segment and inter-segment encodings for better length extrapolation.
problem Improving length extrapolation in language models.
method Bilevel Positional Encoding (BiPE) that separates intra-segment and inter-segment encodings.
result BiPE enhances length extrapolation across various text modalities.
Extreme learning machine (ELM) as a neural network algorithm has shown its good performance, such as fast speed, simple structure etc, but also, weak robustness is an unavoidable defect in original ELM for blended data. We present a new machine learning framework called LARSEN-ELM for overcoming this problem. In our pa…
Mack-Net model combines Mack's model with RNNs for better insurance liability estimation.
problem Accurate estimation of insurance liabilities for better financial decision-making.
method Integrates Mack's reserving model with Recurrent Neural Networks (RNNs).
result Improves accuracy of general insurance liability assessment.
Improved sampling efficiency for inverse problems using variance-reduced diffusion methods.
problem Efficiently estimating noisy scores in inverse problems.
method Developed a nonparametric self-normalized importance sampling estimator and a state-dependent blending rule.
result Improved sample quality for fixed simulation budgets in synthetic targets and PDE-governed inverse problems.
Deep learning method reduces conebeam artifacts in CT imaging.
problem Conebeam artifacts in CT imaging due to cone angle.
method Differentiated backprojection domain deep learning for data-driven inversion.
result Our method outperforms existing iterative methods with reduced runtime complexity.
The ability to perform offline A/B-testing and off-policy learning using logged contextual bandit feedback is highly desirable in a broad range of applications, including recommender systems, search engines, ad placement, and personalized health care. Both offline A/B-testing and off-policy learning require a counterfa…
Multicomponent bilayer structures arise as the ubiquitous plasma membrane in cellular biology and as blends of amphiphilic copolymers used in electrolyte membranes, drug delivery, and emulsion stabilization within the context of synthetic chemistry. We develop the multicomponent functionalized Cahn-Hilliard (mFCH) free…
The most widely used activation functions in current deep feed-forward neural networks are rectified linear units (ReLU), and many alternatives have been successfully applied, as well. However, none of the alternatives have managed to consistently outperform the rest and there is no unified theory connecting properties…
Diffusion models tackle noisy inverse problems with posterior sampling.
problem Efficiently solving general noisy inverse problems.
method Approximation of posterior sampling for diffusion models.
result Diffusion models can handle various noise statistics and nonlinear problems.
Forest-based methods estimate heterogeneous treatment effects, blending strengths for better performance.
problem Estimating heterogeneous treatment effects in randomized and observational studies.
method Causal forests and model-based forests, blending strengths for better performance.
result Local centering of treatment indicator and propensities is crucial for good performance in randomized trials.
HKRR adapts to MIM, overcoming the curse of dimensionality.
problem Understanding when deep networks outperform kernel methods in high dimensions.
method Hyper-kernel ridge regression (HKRR) for multi-index models (MIM).
result HKRR can adaptively learn MIM, overcoming the curse of dimensionality.
New algorithm adapts to optimize non-convex problems efficiently.
problem Inefficient hyperparameter tuning in existing optimization methods.
method Combining geometrization and SARAH algorithms.
result Achieves adaptivity to both accuracy and PL constant.
RPI combines imitation and reinforcement learning to improve policies efficiently.
problem High sample complexity in reinforcement learning.
method Active interleaving between imitation and reinforcement learning, using oracle queries for exploration.
result RPI outperforms existing methods across various domains.
PhysicsNAS generalizes PBL by integrating NAS into neural networks with physical priors.
problem Leveraging physical priors for robust inference in machine learning.
method Physics-based neural architecture search (PhysicsNAS) integrating physical priors and neural networks.
result PhysicsNAS is a top-performer across various physical models and dataset qualities.