Generative Adversarial Networks optimize model parameters for image matching.
problem Optimizing model parameters for accurate image matching.
method Model-Assisted Generative Adversarial Network (GAN) to produce fake images matching true images.
result Best match model parameter values can minimize bias in image recognition.
New insights into neural network complexity reveal better generalization performance.
problem Mysterious generalization in deep models despite high parameter counts.
method Effective dimensionality as a measure of parameter space complexity.
result Double descent behavior in generalization as a function of parameters explained.
This paper presents sampling-based speech parameter generation using moment-matching networks for Deep Neural Network (DNN)-based speech synthesis. Although people never produce exactly the same speech even if we try to express the same linguistic and para-linguistic information, typical statistical speech synthesis pr…
Study examines the cost of tuning hyper-parameters in regression models.
problem Estimating optimal hyper-parameters for regression models.
method Established finite-sample oracle inequalities for hyper-parameter selection.
result Generalization error of selected models shrinks at nearly a parametric rate.
New method estimates GGLM parameters, overcoming non-convexity.
problem Estimating parameters in GGLM with dependencies.
method Monotone operator-based variational inequality method.
result Guarantees for parameter recovery in GLM and GGLM.
Function-space MAP estimation leads to better generalization and robustness.
problem The mismatch between parameter posterior and function posterior in model training.
method Directly estimating the most likely function implied by the model and data.
result Function-space MAP estimation can lead to flatter minima, better generalization, and improved robustness.
A simple modification enables a universal NMT model with language-specific parameters.
problem Creating a universal NMT model that can adapt to different languages and domains.
method Introducing a contextual parameter generator (CPG) that dynamically adjusts model parameters based on source and target language embeddings.
result The system achieves state-of-the-art performance and zero-shot translation, demonstrating the effectiveness of the CPG.
GENIE balances domain-invariant feature learning and gradient alignment for improved DG performance.
problem Domain Generalization (DG) overfitting to domain-specific features
method GENIE (Generalization-ENhancing Iterative Equalizer) optimizer
result Prevents a small subset of parameters from dominating optimization, promoting domain-invariant feature learning
Introduces a new stationary GE-process for gold price analysis.
problem Analyzing gold price data with a flexible stationary process.
method Developed a new stationary GE-process with three parameters. Analyzed synthetic and real gold price data.
result Maximum likelihood estimators can be obtained for the unknown parameters.
Training-free model learns SDE dynamics without training, accelerating parameter studies.
problem High computational cost of simulating parameter-dependent SDEs.
method Training-free conditional diffusion model with joint kernel-weighted Monte Carlo estimator.
result Accurate approximation of conditional distributions across varying parameter values.
Generative approach speeds hyperparameter tuning for machine learning models.
problem Computational infeasibility of cross-validation and difficulty of fully Bayesian hyper-parameter learning.
method Combines optimization-based approximations and amortization techniques.
result Rapid evaluation of hyper-parameters over grids or ranges, supporting predictive tuning and uncertainty quantification.
EIDGM model estimates DE parameters from RCS data.
problem Estimating DE parameters from RCS data with heterogeneities.
method Physics-informed neural network emulator + Wasserstein GAN parameter generator.
result EIDGM accurately captures diverse parameter distributions.
The study provides a theory for deriving generalization guarantees for data-driven algorithm design.
problem Understanding the sufficient amount of data needed for high-performing algorithm design.
method Developed a broadly applicable theory for deriving generalization guarantees that bound the difference between average performance over a training set and expected performance.
result Uncovered a unifying structure to prove extremely general guarantees for various algorithm types.
New method improves neural network robustness by identifying functions rather than parameters.
problem Neural networks' lack of robustness to distribution shifts.
method Identify the function represented by quadratic networks, not their parameters.
result Obtain robust generalization bounds for neural networks.
New meta-learning method improves domain generalization by balancing parameters closer to domain centroids.
problem Improving domain generalization by reducing overfitting to specific domains.
method Arithmetic meta-learning with arithmetic-weighted gradients to balance parameters closer to domain centroids.
result Experimental validation of improved domain generalization performance.
Bayesian model tackles high-dimensional inverse problems efficiently.
problem Estimating spatially-varying parameters in expensive models.
method Multiscale Bayesian inference with deep generative models and MCMC.
result Efficient estimation of global and local parameter features.
Deep networks can approximate functions with fewer learnable parameters than previously thought.
problem High computational costs due to large number of parameters in deep neural networks.
method Theoretical design of ReLU networks with a few intrinsic parameters and numerical experiments.
result ReLU networks with a small number of intrinsic parameters can achieve good approximations of functions.
Quaternion Conformer GAN (QC-GAN) is a parameter-efficient speech enhancement framework that combines a Quaternion Conformer generator with MetricGAN-based training.
problem Speech Enhancement
method Quaternion Conformer GAN
result Achieved a PESQ score of 3.48 with 0.89M parameters, comparable to state-of-the-art models at less than half their size.
Fixed-parameter tractability of private synthetic data generation
problem Generating synthetic data under differential privacy
method Linear programming and subsampled private multiplicative weights method
result Optimal error rates across all regimes
We improve a graph generation model to accurately recover Barabási-Albert graph parameters.
problem Recover Barabási-Albert graph parameters from graph data.
method Use a disentanglement-focused deep autoencoding framework with a sequential LSTM decoder trained on graph data.
result Successfully recover Barabási-Albert graph parameters.
This work creates a deep autoencoding model to interpret graph parameters.
problem Matching observed graph topologies with generative procedures and parameters is challenging.
method Developed a disentanglement-focused Beta-Variational Autoencoder (Beta-VAE) model.
result The model learns disentangled latent variables that represent graph parameters.
New method improves random parameter generation in neural networks.
problem Standard method of generating random weights and biases in neural networks has drawbacks.
method Proposes a new method to generate random parameters ensuring nonlinear sigmoids remain in the input hypercube and uniformly distributed slope angles for activation functions.
result Ensures the most useful nonlinear fragments of sigmoids remain in the input hypercube.
Study on measuring vulnerability of neural network parameters via corruption.
problem Understanding the robustness and generalization of deep neural networks.
method Proposes an indicator to measure parameter robustness via parameter corruption and provides a gradient-based estimation.
result Demonstrates the effectiveness of the proposed indicator and training method in improving parameter robustness and accuracy.
The paper provides a method to find optimal machine learning model parameters with confidence.
problem Finding optimal machine learning model parameters that generalize well to the entire population.
method Constructs valid confidence sets for the optimal parameter using only training data.
result Valid confidence sets for optimal machine learning model parameters can be generated using bootstrapping techniques.
The paper fits a seven-parameter GTS distribution to financial data.
problem Nonexistence of GTS probability density function makes MLE inadequate.
method Used fractional Fourier transform to circumvent MLE and provide good parameter estimation.
result The GTS distribution fits financial data significantly better than other models.
We study multi-parameter Carnot-Caratheodory balls, generalizing results due to Nagel, Stein, and Wainger in the single parameter setting. The main technical result is seen as a uniform version of the theorem of Frobenius. In addition, we study maximal functions associated to certain multi-parameter families of Carnot-…
HyperGAN generates diverse neural network parameters for improved performance and uncertainty.
problem Overconfidence of neural networks in out-of-distribution data.
method Generative model using a novel mixer to learn a distribution of neural network parameters.
result HyperGAN can generate parameters that perform competitively with fully supervised learning and provide better uncertainty estimates.
Lee's work on twisted torus knots with Fibonacci parameters is extended to Horadam parameters.
problem Classifying twisted torus knots with Horadam parameters.
method Using recursive Horadam parameters to generalize Lee's work on Fibonacci parameters.
result Families of twisted torus knots with Horadam parameters are provided.
Proposes a new method for generating random parameters in neural networks.
problem Improving randomized learning of feedforward neural networks.
method Randomly selects slope angles, rotates activation functions, and distributes them across the input space.
result The method gives better results than the common approach, especially for complex target functions.
NPAS trains neural networks with a fixed parameter budget, improving performance and compactness.
problem Training neural networks requires memory, and existing methods struggle with arbitrary parameter budgets.
method NPAS learns to share parameters automatically, covering low and high budgets.
result NPAS and SSNs improve network performance and compactness across various tasks.
FNFs model parameter-dependent densities by combining a fixed flow with a polynomial parameter-dependent transformation.
problem Learning a separate flow for every parameter configuration is intractable.
method Factorizable Normalizing Flows (FNFs) represent the parameter-dependent density as a fixed flow for a reference configuration and a learnable polynomial transformation factorized over parameters.
result FNFs enable the recovery of the combined effect of multiple parameters without sampling their joint space, providing a scalable and interpretable solution.
Learning the parameters of a (potentially partially observable) random field model is intractable in general. Instead of focussing on a single optimal parameter value we propose to treat parameters as dynamical quantities. We introduce an algorithm to generate complex dynamics for parameters and (both visible and hidde…
CAM-GAN improves GANs for continual learning with efficient feature map transformations.
problem Efficient continual learning for GANs with reduced parameter growth.
method Designing and leveraging parameter-efficient feature map transformations, including global and task-specific parameters, residual bias, and Fisher information matrix.
result Significantly improved model performance and high-quality samples with fewer parameters.
Double descent in transfer learning explained for linear regression problems.
problem Understanding generalization errors in transferring parameters between overparameterized linear regression tasks.
method Analytical characterization of generalization error in terms of transfer learning factors.
result Generalization error follows a two-dimensional double descent trend controlled by transfer learning factors.
The paper introduces canonical parameters for marginally trapped surfaces in Minkowski space.
problem Determining marginally trapped surfaces in Minkowski space.
method Introducing canonical parameters and proving existence and uniqueness theorems.
result Every marginally trapped surface is determined by three smooth functions.
Supervised learning frequently boils down to determining hidden and bright parameters in a parameterized hypothesis space based on finite input-output samples. The hidden parameters determine the attributions of hidden predictors or the nonlinear mechanism of an estimator, while the bright parameters characterize how h…
We study the problem of estimating the parameters of a regression model from a set of observations, each consisting of a response and a predictor. The response is assumed to be related to the predictor via a regression model of unknown parameters. Often, in such models the parameters to be estimated are assumed to be c…
Novel method embeds generative model into Bayesian optimization for HD cardiac model parameter estimation.
problem High-dimensional optimization of patient-specific cardiac model parameters with limited data.
method Embeds a generative variational auto-encoder into the objective function of Bayesian optimization.
result Improves accuracy of parameter estimation with more than 10x gain in efficiency.
A new method infers graph structure and parameters using a single generative flow network.
problem Bayesian Network structure and parameter inference from data.
method Single GFlowNet with two-phase sampling: DAG generation followed by parameter assignment.
result Accurate approximation of joint posterior distribution over graph structure and parameters.
The article reviews how to set stochastic volatility model parameters.
problem Choosing parameters for stochastic volatility models.
method Examines existing literature on various methods.
result Different approaches to setting stochastic volatility parameters.
Pruning neural networks can improve test accuracy even with significant parameter reduction.
problem The tradeoff between generalization and stability in neural network pruning.
method Analysis of pruning behavior over training, focusing on instability and its relation to generalization.
result Pruning's benefit to generalization increases with its instability.
Transformer learns to estimate negative binomial parameters efficiently.
problem Parameter estimation for over-dispersed count data in large screens.
method Pre-trained transformer trained on synthetic data generation to invert parameter to count transformation.
result Method of moments provides faster, more efficient, and better-calibrated estimates.
Generatability in metric spaces studied with novel novelty parameters.
problem Understanding generatability in metric spaces with asymmetric novelty parameters.
method Introducing (ε,ε′)-closure dimension to characterize uniform and non-uniform generatability. result Generatability is stable across novelty scales in doubling spaces but can be highly scale-sensitive in general metric spaces.
Study families of Morse functions for manifolds with boundary.
problem Characterize degeneracies in 1-parameter families of Morse functions.
method List all possible degeneracies in generic 1-parameter families.
result Identified all degeneracies in generic 1-parameter families.
Paper analyzes GMM for separable data with various parameter structures.
problem Classifying separable data with logistic models and their generalizations.
method Introduces and analyzes Generalized Margin Maximizer (GMM) for logistic models with specific parameter structures.
result GMM outperforms max-margin classifiers in various parameter settings and structures.
Improved ridge estimators avoid tuning parameters for high-dimensional data.
problem Difficulty in calibrating tuning parameters for ridge estimators.
method Developed modified ridge estimators that eliminate tuning parameters.
result Modified ridge estimators outperform standard methods in prediction accuracy.
TensorGuide improves LoRA efficiency and expressivity through joint tensor-train optimization.
problem Limited expressivity and generalization of standard LoRA.
method TensorGuide uses a unified tensor-train structure with controlled Gaussian noise to generate correlated low-rank matrices.
result TensorGuide achieves superior accuracy and scalability with fewer parameters compared to standard LoRA and TT-LoRA.
Quantum model generates financial data with fewer parameters.
problem Generating financial data with fewer parameters.
method Applied time-series quantum generative model to financial data.
result Fewer parameters required compared to classical methods.