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 17 of 17 for “"Empirical Risk Minimization"”.
-
Applications of empirical processes in learning theory : algorithmic stability and generalization bounds
… on concentration inequalities and tools from empirical process theory. We obtain theoretical results and demonstrate their applications to machine learning. First, we show how various notions of stability upper- and lower-bound the bias and variance of several estimators of the expected …
-
Large-scale optimization Methods for data-science applications
… of a strict lower bound (like what happened in empirical risk minimization in machine learning). We introduce a new functional measure called the growth constant for the convex objective function, that measures how quickly the level sets grow relative to the function value, and that plays a …
-
TOWARDS RELIABLE AI UNDER DISTRIBUTION SHIFTS: A DATA-CENTRIC PERSPECTIVE
… We theoretically show that when training with empirical risk minimization, label noise exacerbates the effect of spurious correlations in the training data. Second, we introduce two data-centric strategies to diagnose and improve quality of data. To detect mislabeled data, we propose an …
-
Empirical Bayes via ERM and Rademacher complexities: the Poisson model
We consider the problem of empirical Bayes estimation for (multivariate) Poisson 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 …
-
Phase Retrieval Under a Generative Prior
… a generative neural network. By formulating an empirical risk minimization problem and directly optimizing over the domain of the generator, we show that the objective’s energy landscape exhibits favorable global geometry for gradient descent with information theoretically optimal sample …
-
Data-driven robust solution schemes for sequential decision making
… sample average approximation—also referred to as empirical risk minimization in the machine learning literature—often suffer from poor out-of-sample performance when data is limited. To address this issue, the dissertation proposes a data-efficient alternative to sample average approximation for …
-
Below P vs NP : fine-grained hardness for big data problems
… string processing problems. ** Lower bounds for empirical risk minimization such as kernel support vectors machines and other kernel machine learning problems. All of these problems have polynomial time algorithms, but despite extensive amount of research, no near-linear time algorithms have been …
-
Topics in non-convex optimization and learning
… two common practices in deep learning, namely empirical risk minimization (ERM) and normalization. Specifically, I show (1) training on convex combinations of samples improves model robustness and generalization, and (2) a good initialization is sufficient for training deep residual networks …
-
High-Dimensional Inference with Heterogeneous Data
… and real data. We then propose a sample-weighted empirical risk minimization method for inferring change points in GLMs which we call `Weighted ERM`. We prove that our previous AMP algorithm can be tailored to mimic `Weighted ERM`, allowing us to obtain precise guarantees on the performance of …
-
Learning inside the prediction function
… laws. Finally, we propose Functional risk minimization(FRM), an alternative framework to the standard Empirical risk minimization(ERM) setting where loss functions act in function space rather than output space. We show how we can make learning in this new framework efficient and can …
-
Gradient Subgroup Scanning for Distributionally and Outlier Robust Models
Traditional machine learning methods such as empirical risk minimization (ERM) frequently encounter the issue of achieving high accuracy on average but low accuracy on certain subgroups, especially when there exist spurious correlations between the input data and label. Previous approaches for …
-
Robustness and generalization guarantees for statistical learning of generative models
… standard methods based on the theory of empirical processes with ideas from optimal transport and signal recovery, we formally address the generalization and robustness guarantees for the existing and newly suggested algorithms. More specifically, we consider the following three problems: …
-
Non-asymptotic bounds for prediction problems and density estimation.
… optimal prediction rule based on penalized empirical risk minimization algorithm. We show that the proposed estimator is able to take advantage of the possible sparse structure of the problem by providing probabilistic bounds for its performance.
-
On Principled Modeling of Inductive Bias in Machine Learning
… bias modeling. By decomposing the regularized empirical risk minimization, this thesis introduces two different perspectives: value-guided modeling through regularization, and data-centric modeling through training data manipulation. In value-guided modeling, we define a quantity called …
-
Hypothesis testing and causal inference with heterogeneous medical data
… with conventional learning paradigms such as empirical risk minimization. Acknowledging this spurious effect, we develop a new learning principle inspired by causal insights that provably generalizes to test data sampled from a larger set of distributions different from the training …
-
Large scale optimization for machine learning
… machine learning problems are fundamentally empirical risk minimization problems, large scale optimization plays a key role in building a large scale machine learning system. However, scaling optimization algorithms like stochastic gradient descent (SGD) in a distributed system raises some …
-
Unsupervised Learning : Model-guided and Model-agnostic Approaches
… potential of machine learning algorithms beyond empirical risk minimization and extend them to learning non-trivial representations of the data. At the core of such learning are two distinct principles - model-agnostic representation learning and model-guided inference. The goal of this thesis is …