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 106 for “"Theoretical Guarantees"”.
-
Finite precision deep learning with theoretical guarantees
… in finite precision deep learning abound, theoretical guarantees on network accuracy are elusive. The work presented in this dissertation builds a theoretical framework for the implementation of deep learning in finite precision. For inference, we theoretically analyze the worst-case …
-
Theoretical guarantees and complexity reduction in information planning
… Our contributions are three-fold: (i) we provide theoretical guarantees for the greedy algorithm used in the submodular monotone case when it is applied to dierent problem settings: (1) non-monotone rewards, (2) budget constraints, (3) settings where only a set of latent variables is of relevance; …
-
Latent Structure Estimation for Panel Data and Theoretical Guarantees for Stochastic Optimization
… many of these surprisingly lack fundamental theoretical grounding. The central theme of this work is adopting tools from statistics to bridge the gap between theory and application in machine learning and optimization. In this thesis, we investigate several fundamental problems arising from …
-
Distributed Singular Value Decomposition Through Least Squares
… and involve optimization algorithms with some theoretical guarantees, though many of these techniques are not scalable in nature. We show the efficacy of a distributed stochastic gradient descent algorithm by implementing parallelized alternating least squares and prove theoretical guarantees …
-
Exact geometry algorithms for robotic motion planning
… algorithms, it often comes at the cost of theoretical guarantees and performance. In this thesis, we explore deterministic motion planning algorithms that have explicit knowledge of the geometry of the underlying problems. By exploiting this geometry, we give algorithms that can achieve …
-
Understanding and Overcoming Optimization Barriers in Non-convex and Non-smooth Machine Learning
… simplicity, these methods are often lacking in theoretical guarantees. To design machine learning algorithms that are less data-hungry while ensuring theoretical guarantees on both computational efficiency and output validity, it is essential to better understand and leverage the rich structure …
-
Diverse sampling of streaming data
… algorithms in practice and compares them to the theoretical guarantees.
-
Finding Interesting Subgraphs with Guarantees
… easy to implement. However, they come with no theoretical guarantees on the quality of the solution, which makes it difficult to assess how the discovered subgraphs compare to an optimal solution, which in turn affects the data mining task at hand. For instance, in anomaly detection, solutions …
-
SAMoSSA: Multivariate Singular Spectrum Analysiswith Stochastic Autoregressive Noise
… via Ordinary Least Squares (OLS). However, a theoretical underpinning of multi-stage learning algorithms involving both deterministic and stationary components has been absent in the literature despite its pervasiveness. We tackle this issue by establishing desirable theoretical guarantees for …
-
Improved Gaussian process approximations for spatial and flow fields
… outperform existing methods, have compelling theoretical guarantees, and are applicable to a broad class of priors - stationary priors whose covariance functions have well-defined spectral densities. Since many spatial fields are highly non-stationary, in Chapter 4 I construct a new class of …
-
Machine learning and causality: Building efficient, and reliable models for decision-making
… applied to many problems, but the lack of strong theoretical guarantees has led to many unexpected failures. Models that perform well on the training distribution tend to break down when applied to different distributions; small perturbations can “fool” the trained model and drastically change its …
-
Learning Causal Representations for Generalization and Adaptation in Supervised, Imitation, and Reinforcement Learning
… time. To this end, we propose a framework, with theoretical guarantees under rather general assumptions over the underlying causal diagram, that first identifies direct causes of a given target from observations and then use those causes to build invariant predictors that are able to generalize …
-
Novel first-order methods for bilevel and minimax optimization.
… develops novel first-order methods with strong theoretical guarantees for solving both classes of problems. Specifically, we study a class of constrained minimax problems and propose efficient augmented Lagrangian methods with complexity guarantees for both nonconvex-concave and …
-
CLAIRE makes machine translation BLEU no more
… translation systems which is inexpensive, has theoretical guarantees, and correlates strongly in practice with more expensive human judgments of system quality. Our analysis reverses several major tenants of the mainstream machine translation research agenda, suggesting in particular that the …
-
Enabling the Rust Compiler to Reason about Fork/Join Parallelism via Tapir
… and the OpenCilk parallelism platform’s strong theoretical guarantees for performance of parallel programs. I compare Rust + Cilk to existing librarybased parallelism solutions in Rust such as Rayon, as well as to C programs parallelized with OpenCilk, based on performance and ergonomics. I find …
-
Sampling-based Algorithms for Fast and Deployable AI
… present sampling-based algorithms with provable guarantees to alleviate the increasingly prohibitive costs of training and deploying modern AI systems. At the core of this thesis lies importance sampling, which we use to construct representative subsets of inputs and compress machine learning …
-
Worst-case Performance of Popular Approximate Nearest Neighbor Search Implementations: Guarantees and Limitations
… datasets in practice, but they have limited theoretical guarantees. We study the worst-case performance of recent graph-based approximate nearest neighbor search algorithms, such as HNSW, NSG and DiskANN. For DiskANN, we show that its “slow preprocessing” version provably supports approximate …
-
Empirical Bayes via ERM and Rademacher complexities: the Poisson model
… means. Existing solutions that have been shown theoretically optimal for minimizing the regret (excess risk over the Bayesian oracle that knows the prior) have several shortcomings. For example, the classical Robbins estimator does not retain the monotonicity property of the Bayes estimator and …
-
Interpreting and optimizing data
… we found that is possible to provide theoretical guarantees for the intervention results when we model the data with a Gaussian process. The second goal was to map various data, including sentences and medical images, to a simple, understandable latent space, in which an intervention …
-
Robotic Search Planning In Large Environments with Limited Computational Resources and Unreliable Communications
… of constructing receding horizon paths provide theoretical worst-case performance guarantees. Our result can be interpreted as ensuring that the receding horizon path performs no worse in expectation than a given sub-optimal search path. This result is especially practical for subsea …
Page 1 of 6