When the available data of a target speaker is insufficient to train a high quality speaker-dependent neural text-to-speech (TTS) system, we can combine data from multiple speakers and train a multi-speaker TTS model instead. Many studies have shown that neural multi-speaker TTS model trained with a small amount data f…
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.
168,695 papers · 148 categories
Trend · papers per month
48 results for “training data dependence”
ABC method analyzes diffusion model dependence without retraining.
problem Difficulties in characterizing diffusion models' dependence on training data.
method Ablation-based counterfactuals using model components trained on different splits.
result Demonstrates limits of training data attribution and existence of unattributable samples.
BAM model learns graph structure from data with robustness across linear and non-linear dependencies.
problem Detecting dependencies in datasets for graph structure learning.
method Proposes BAM, a neural network model using structural equation models and Chebyshev polynomials for training, with bilinear attention mechanism.
result Demonstrates robust generalizability and superior performance in graph estimation.
Optimal kernel in KR can be data-dependent, improving model performance.
problem Fixed kernel in KR limits model performance.
method Considered data-dependent kernels for KR, using posterior covariance.
result Data-dependent kernel choice leads to optimal performance.
Existing Rademacher complexity bounds for neural networks rely only on norm control of the weight matrices and depend exponentially on depth via a product of the matrix norms. Lower bounds show that this exponential dependence on depth is unavoidable when no additional properties of the training data are considered. We…
The paper highlights how machine learning calibrations can be biased by training data.
problem Machine learning calibrations can be biased by the training data, affecting downstream analyses.
method The paper examines simulation-based and data-based calibrations, highlighting their prior dependence and proposing solutions.
result A recently proposed Gaussian Ansatz approach can avoid some biases in simulation-based calibrations.
PAC-Bayesian theory applied to data-dependent hypothesis sets yields uniform generalization bounds.
problem Proving uniform generalization bounds for data-dependent hypothesis sets.
method Applying PAC-Bayesian framework on 'random sets' and considering data-dependent hypothesis sets.
result Data-dependent uniform generalization bounds are proven, providing tighter and unified results.
The study characterizes diffusion model generalization using data-dependent ridge manifolds.
problem Understanding where diffusion model-generated samples lie when not memorizing the training set.
method Introduced a time-dependent family of log-density ridge manifolds to characterize reverse-time inference.
result Generated samples evolve by a reach-align-slide mechanism, controlled by normal and tangential components of training error.
Convolutional analysis operator learning (CAOL) enables the unsupervised training of (hierarchical) convolutional sparsifying operators or autoencoders from large datasets. One can use many training images for CAOL, but a precise understanding of the impact of doing so has remained an open question. This paper presents…
uTSGAN improves on TSGAN for generating time series data.
problem Challenges in generating time-dependent data.
method Unified training of independent networks in TSGAN.
result uTSGAN outperforms TSGAN in 80% of benchmark datasets.
In this paper, we propose a novel dynamic ensemble selection framework using meta-learning. The framework is divided into three steps. In the first step, the pool of classifiers is generated from the training data. The second phase is responsible to extract the meta-features and train the meta-classifier. Five distinct…
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.
New neural process models produce correlated predictions for better estimation tasks.
problem Need for models that can handle correlated predictions for tasks like weather forecasting.
method Developed new Neural Process models that can produce correlated predictions and support exact maximum likelihood training.
result Improved predictive performance on various experiments with synthetic and real data.
Improved pruning method finds winning neural network subnetworks.
problem Finding a small subnetwork that performs as well as a full neural network.
method Data-dependent pruning criterion using gradient of training loss.
result Data-dependent pruning improves existing pruning algorithms.
Improves normalizing flows by incorporating data dependencies.
problem Current normalizing flow learning assumes independent data, leading to errors.
method Proposes a likelihood objective with dependencies and efficient learning algorithm.
result Improves density estimation and data generation on real-world data.
We improve the robustness of Deep Neural Net (DNN) to adversarial attacks by using an interpolating function as the output activation. This data-dependent activation remarkably improves both the generalization and robustness of DNN. In the CIFAR10 benchmark, we raise the robust accuracy of the adversarially trained Res…
Signature Kernel Scoring Rule: A Spatio-Temporal Diagnostic for Probabilistic Weather Forecastingstat.ML
Signature kernel scoring rule improves weather forecasting by capturing temporal and spatial dependencies.
problem Lack of suitable scoring rules for probabilistic weather forecasting.
method Reframe weather variables as continuous paths using iterated integrals (signature kernels) to capture temporal and spatial dependencies.
result Signature kernel scoring rule outperforms conventional methods in weather forecasting, especially for long-term forecasts.
Generalization Guarantees for Representation Learning via Data-Dependent Gaussian Mixture Priorsstat.ML
The study improves representation learning bounds using data-dependent Gaussian mixtures.
problem Improving generalization in representation learning.
method Established bounds using relative entropy and MDL of latent variables.
result The approach significantly improves generalization over existing methods.
Paper establishes a generalization bound for gradient flow using a data-dependent kernel.
problem Understanding the generalization properties of gradient-based optimization methods.
method Establishes a generalization bound for gradient flow through a data-dependent kernel called the loss path kernel (LPK).
result The LPK captures the entire training trajectory and leads to tighter generalization guarantees.
The paper improves PAC-Bayes bounds for data-dependent predictors.
problem Guaranteeing the quality of predictions on unseen examples.
method Basic PAC-Bayes inequality for stochastic kernels, leading to various bounds.
result Validates PAC-Bayes bounds without fixed 'data-free' priors and bounded losses.
Analyzes why neural networks generalize beyond training data.
problem Understanding why neural networks generalize beyond training data.
method Examined loss landscapes of neural networks to identify the mismatch between training and test losses.
result Identified the 'LU mechanism' explaining grokking in various tasks.
New bounds ensure reliable deep learning performance without model changes.
problem Certifying deep neural networks' reliability without altering them.
method Data-dependent generalization bounds that apply directly to trained models.
result Achieves meaningful generalization guarantees for large, unaltered deep networks.
We reformulate data-dependent constraints to ensure they are always met with high probability.
problem Ensuring fairness and stability in machine learning models with data-dependent constraints.
method Calibrated reformulation of constraints to guarantee satisfaction with a specified probability.
result Our method guarantees that fairness constraints are met at test time with high probability.
Captures data influence changes during training.
problem Traditional influence functions fail for modern training methods.
method Formalized trajectory-specific LOO influence, using data value embedding.
result Data influence varies by training stage, early and late stages have greater impact.
We establish a theoretical link between adversarial training and operator norm regularization for deep neural networks. Specifically, we prove that -norm constrained projected gradient ascent based adversarial training with an -norm loss on the logits of clean and perturbed inputs is equivalent to data-…
Study shows accuracy of neural networks depends more on error location than percentage of error.
problem Effect of noise on accuracy in incremental learning neural networks.
method Empirical study using Perceptron, Feed Forward Neural Network, and Radial Basis Function Neural Network.
result Accuracy of neural networks is more dependent on error location than the percentage of error.
seq2graph: Discovering Dynamic Dependencies from Multivariate Time Series with Multi-level Attentioncs.LG
Discovering temporal lagged and inter-dependencies in multivariate time series data is an important task. However, in many real-world applications, such as commercial cloud management, manufacturing predictive maintenance, and portfolios performance analysis, such dependencies can be non-linear and time-variant, which …
DP-SGD analysis shows many datapoints leak less privacy than previously thought.
problem Empirical evidence suggests DP-SGD leaks less privacy than current analysis predicts.
method Developed a per-instance DP analysis of DP-SGD, introducing dependence on dataset distribution.
result Formally shows DP-SGD leaks significantly less privacy for many datapoints on common benchmarks.
Derives ideal train/test split for ridge regression in large data limit.
problem Finding optimal train/test split for ridge regression in large data scenarios.
method Mathematical derivation of optimal train/test split, considering ridge tuning parameter and asymptotic behavior.
result The optimal train/test split for ridge regression in the large data limit depends weakly on the ridge tuning parameter alpha.
Analyzes error sources in global feature effect estimation methods.
problem Unexplored error sources in global feature effect estimation methods.
method Systematic, estimator-level analysis of bias and variance.
result Holdout data is theoretically cleanest, but estimation variance depends on sample size and model characteristics.
Training Well-Generalizing Classifiers for Fairness Metrics and Other Data-Dependent Constraintscs.LG
Classifiers can be trained with data-dependent constraints to satisfy fairness goals, reduce churn, achieve a targeted false positive rate, or other policy goals. We study the generalization performance for such constrained optimization problems, in terms of how well the constraints are satisfied at evaluation time, gi…
A new principle for extrapolating regression outside training data.
problem Regression extrapolation when predictions are outside training data range.
method Data-adaptive marginal transformation and simple relationship assumption.
result Progression method offers guarantees on approximation error beyond training data range.
Neural networks can learn kernel machines with a data-dependent kernel.
problem Can neural networks in the rich feature learning regime learn a kernel machine?
method Demonstrated silent alignment effect in neural networks, showing they can learn a kernel machine with a data-dependent kernel.
result Neural networks in the rich feature learning regime can learn a kernel machine with a data-dependent kernel due to silent alignment.
Proposes a method to estimate time-dependent probability density functions using binary classifiers.
problem Estimating time-dependent probability density functions of stochastic processes.
method Trains a time-dependent binary classifier to discriminate between realizations of a stochastic process at two nearby time instants.
result Explicitly models and accurately reconstructs complex time-dependent, multi-modal, and near-degenerate densities.
Estimates KRR risk from training data for various kernels and hyperparameters.
problem Predicting the generalization error of Kernel Ridge Regression.
method Introduces SCT and KARE to approximate KRR risk from training data.
result KARE provides an excellent approximation of KRR risk and helps select good kernels.
WeldNet reduces complex dynamics to simpler, manageable segments.
problem Complex, high-dimensional time-dependent datasets from physical processes are costly to simulate.
method Windowed Encoders for Learning Dynamics, splitting time domain into windows for nonlinear dimension reduction and propagator training.
result WeldNet captures nonlinear latent structures and dynamics, outperforming existing methods.
Diffusion-GAN uses diffusion to improve GAN training stability and realism.
problem Stability and realism issues in training GANs.
method Diffusion-GAN employs a forward diffusion chain to generate Gaussian-mixture distributed instance noise, with adaptive diffusion process and timestep-dependent discriminator.
result Diffusion-GAN produces more realistic images with higher stability and data efficiency.
SpeakerStew verifies 46 languages with reduced training and inference costs.
problem Speaker verification for 46 languages with smart speaker interactions.
method Pooling multilingual data, triage between text-dependent and text-independent models.
result Training on multiple languages generalizes well and reduces computational requirements.
The paper shows robustness and generalization are closely connected via data-dependent bounds.
problem Connecting robustness and generalization in machine learning.
method Data-dependent generalization bounds that reduce dependence on covering number and hypothesis space.
result Proves robustness implies generalization, with near-exponential improvements in various situations.
Despite recent innovations in network architectures and loss functions, training RNNs to learn long-term dependencies remains difficult due to challenges with gradient-based optimisation methods. Inspired by the success of Deep Neuroevolution in reinforcement learning (Such et al. 2017), we explore the use of gradient-…
Deep signature/log-signature FBSDE algorithm improves accuracy and training time.
problem Solving FBSDEs with state and path dependent features.
method Incorporates deep signature/log-signature transformation into RNN model.
result Improves accuracy and training time compared to existing methods.
Smoothness analysis of adversarial training reveals constraints cause more non-smoothness.
problem Non-smoothness of adversarial training loss function.
method Analyzed the smoothness of adversarial training loss function using optimal attacks for model parameters.
result The constraint causes more non-smoothness than constraint.
New attack reveals memorization patterns in pre-trained LLMs.
problem Determining if a data point was part of a pre-trained LLM's training set.
method Adapts MIA statistical tests to LLM's perplexity dynamics of subsequences.
result Significantly outperforms prior approaches in membership inference attacks.
Pac-Bayes bounds are among the most accurate generalization bounds for classifiers learned from independently and identically distributed (IID) data, and it is particularly so for margin classifiers: there have been recent contributions showing how practical these bounds can be either to perform model selection (Ambrol…
Most previous works usually explained adversarial examples from several specific perspectives, lacking relatively integral comprehension about this problem. In this paper, we present a systematic study on adversarial examples from three aspects: the amount of training data, task-dependent and model-specific factors. Pa…
Paper introduces data-dependent SSP for private linear and logistic regression.
problem Private linear and logistic regression with better performance.
method Data-dependent sufficient statistic perturbation (SSP) for linear and logistic regression.
result Data-dependent SSP outperforms state-of-the-art methods for linear and logistic regression.
A new method for deep learning under distribution shift by iteratively refining importance weighting.
problem Handling distribution shift in deep learning models when training and test data distributions differ.
method Dynamic Importance Weighting (dynamic IW) that iterates between weight estimation and weighted classification, using a pre-trained feature extractor and stochastic optimization.
result Dynamic IW outperforms state-of-the-art methods in experiments with various types of distribution shift on multiple datasets.
We study the recently introduced stability training as a general-purpose method to increase the robustness of deep neural networks against input perturbations. In particular, we explore its use as an alternative to data augmentation and validate its performance against a number of distortion types and transformations i…