Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 20 for “"generalization error"”.
-
Information-theoretic bounds in learning algorithms
… is in the area of mutual information-based generalization error bounds of supervised learning algorithms. Our bound is constructed in terms of the mutual information between each individual training sample and the output of the learning algorithm, which requires weaker conditions on the loss …
-
Learning and Smooth Simultaneous Estimation of Errors Based on Empirical Data
… of a new sample point is called a hypothesis' "generalization error."
-
Semantic role labeling using rich morphological features
… is also introduced that significantly decreases generalization error, leading to state-of-the-art argument role classification results.
-
Beneficial Initializations in Over-Parameterized Machine Learning Problems
… and ImageNet and also prove that it reduces the generalization error of any interpolating solution with high probability. By extending our analysis of transfer learning in linear regression, we present an approach for transfer learning in kernel regression. Namely, we demonstrate that transfer …
-
ARDA : automatic relational data augmentation for machine learning
… information would result in improving the generalization of the ML models. We design an end-to-end system that takes as input a data set, a ML model and access to unstructured data, and outputs an augmented data set such that training the model on this dataset results in better …
-
Information-theoretic limitations of distributed information processing
… we first study the relationship between the generalization capability of a learning algorithm and its stability property measured by the mutual information between its input and output, and then derive achievability results on the generalization error of adaptively composed learning …
-
A theory of (almost) zero resource speech recognition
… entropy prior, is shown to provably minimize the generalization error of any probabilistic model (e.g. HMMs). The second part examines application-specific loss functions such as cluster purity and perplexity. Empirical results on a variety of tasks -- acoustic event detection, class-based …
-
On feature selection : learning with exponentially many irreverent features as training examples
… performed exactly, we give a rigorous bound for generalization error under feature selection. The search heuristics typically used are then immediately seen as trying to achieve the error given in our bounds, and succeeding to the extent that they succeed in solving the optimization. The bound …
-
Scaling Laws for Deep Learning
… realizable case that DL is in fact dominated by error sources very far from the lower error limit. We conclude by building on the gained theoretical understanding of the scaling laws’ origins. We present a conjectural path to eliminate one of the current dominant error sources — through a data …
-
A Geometrical Approach to Machine Learning: From Complexity Measures to Quantization
… dimension. This new quantity provably bounds the generalization error under mild assumptions on the model. Furthermore, simulations on standard data sets and popular model architectures show that 2sED correlates well with the training error. For Markovian models, we show how to efficiently …
-
New Models qnd Algorithms for Bandits and Markets
… of model class in supervised learning, and the generalization error of the best fit from that class, such as the celebrated VC-theory. However, an analogous notion of dimensionality, which relates a generic structural assumption on rewards to regret rates in an online optimization problem, is …
-
Advances in Reinforcement Learning for Decision Support
… framework that yields a simple and scalable generalization of curiosity that is robust to all types of stochasticity, and demonstrate state-of-the-art results in a popular benchmark. In the second instance, we formalize a unifying perspective on inverse decision modeling that generalizes …
-
Compound-Gaussian-regularized inverse problems: theory, algorithms, and neural networks
… of the optimization landscape geometry. Third, a generalization on the newly constructed CG regularized least squares iterative algorithm is developed, theoretically analyzed, and unrolled to yield a novel state-of-the-art DNN that provides a partial learning of the prior distribution constrained …
-
Stability of machine learning algorithms
… training samples. Incorporating DBI with the generalization error (GE), we propose a two-stage algorithm for selecting the <em>most accurate and stable</em> classifier. The proposed classifier selection method introduces the statistical inference thinking into the machine learning society. Our …
-
Automated and Provable Privatization for Black-Box Processing
… theory also connects algorithmic stability and generalization error, demonstrating win-win situations in machine learning that simultaneously improve PAC Privacy and learning performance. c). Automated Privacy-Preserving Solutions: Theoretically, we characterize the tradeoff between required …
-
Learning Seismic Waves for Imaging the Earth
… real seismic data in training may reduce the generalization error for the network trained only on synthetic data. We thus develop a semi-supervised learning method and train generative adversarial networks with real data without real labels. Both synthetic and field examples show that the …
-
Exploring Loss Functions in Machine Learning
… descent, we show that the the tree loss’s generalization error is asymptotically better than the cross entropy loss’s. We then validate these theoretical results on synthetic data, image data (CIFAR100, ImageNet), and text data (Twitter).We also investigate the application of contrastive …
-
Similarity modeling for machine learning
… optimal partition of the data by minimizing the generalization error of the learned classifiers associated with the data partitions. Regarding to our sparse similarity modeling methods, we propose a novel $\ell^{0}$ regularized $\ell^{1}$-graph ($\ell^{0}$-$\ell^{1}$-graph) to improve …
-
Online and active learning of big networks: theory and algorithms
… active learning approach on a graph, based on generalization error bound minimization. In particular, I present a data-dependent error bound for a graph-based learning method, namely learning with local and global consistency (LLGC). I show that the empirical transductive Rademacher complexity …
-
Learning from Geometry
… principal angles lead to smaller classification error, motivating a linear transform that optimizes principal angles. This linear transformation, termed TRAIT, also preserves some specific features in each class, being complementary to a recently developed Low Rank Transform (LRT). Moreover, when …