Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userOn Tilted Losses in Machine Learning: Theory and Applications
77
0
0.0
(
0
)
Added by
Tian Li
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Exponential tilting is a technique commonly used in fields such as statistics, probability, information theory, and optimization to create parametric distribution shifts. Despite its prevalence in related fields, tilting has not seen widespread use in machine learning. In this work, we aim to bridge this gap by exploring the use of tilting in risk minimization. We study a simple extension to ERM -- tilted empirical risk minimization (TERM) -- which uses exponential tilting to flexibly tune the impact of individual losses. The resulting framework has several useful properties: We show that TERM can increase or decrease the influence of outliers, respectively, to enable fairness or robustness; has variance-reduction properties that can benefit generalization; and can be viewed as a smooth approximation to a superquantile method. Our work makes rigorous connections between TERM and related objectives, such as Value-at-Risk, Conditional Value-at-Risk, and distributionally robust optimization (DRO). We develop batch and stochastic first-order optimization methods for solving TERM, provide convergence guarantees for the solvers, and show that the framework can be efficiently solved relative to common alternatives. Finally, we demonstrate that TERM can be used for a multitude of applications in machine learning, such as enforcing fairness between subgroups, mitigating the effect of outliers, and handling class imbalance. Despite the straightforward modification TERM makes to traditional ERM objectives, we find that the framework can consistently outperform ERM and deliver competitive performance with state-of-the-art, problem-specific approaches.
rate research
Read More
Optimal Transport (OT) theory has seen an increasing amount of attention from the computer science community due to its potency and relevance in modeling and machine learning. It introduces means that serve as powerful ways to compare probability distributions with each other, as well as producing optimal mappings to minimize cost functions. In this survey, we present a brief introduction and history, a survey of previous work and propose directions of future study. We will begin by looking at the history of optimal transport and introducing the founders of this field. We then give a brief glance into the algorithms related to OT. Then, we will follow up with a mathematical formulation and the prerequisites to understand OT. These include Kantorovich duality, entropic regularization, KL Divergence, and Wassertein barycenters. Since OT is a computationally expensive problem, we then introduce the entropy-regularized version of computing optimal mappings, which allowed OT problems to become applicable in a wide range of machine learning problems. In fact, the methods generated from OT theory are competitive with the current state-of-the-art methods. We follow this up by breaking down research papers that focus on image processing, graph learning, neural architecture search, document representation, and domain adaptation. We close the paper with a small section on future research. Of the recommendations presented, three main problems are fundamental to allow OT to become widely applicable but rely strongly on its mathematical formulation and thus are hardest to answer. Since OT is a novel method, there is plenty of space for new research, and with more and more competitive methods (either on an accuracy level or computational speed level) being created, the future of applied optimal transport is bright as it has become pervasive in machine learning.
This paper provides a first study of utilizing energy harvesting for sustainable machine learning in distributed networks. We consider a distributed learning setup in which a machine learning model is trained over a large number of devices that can harvest energy from the ambient environment, and develop a practical learning framework with theoretical convergence guarantees. We demonstrate through numerical experiments that the proposed framework can significantly outperform energy-agnostic benchmarks. Our framework is scalable, requires only local estimation of the energy statistics, and can be applied to a wide range of distributed training settings, including machine learning in wireless networks, edge computing, and mobile internet of things.
Feature selection, in the context of machine learning, is the process of separating the highly predictive feature from those that might be irrelevant or redundant. Information theory has been recognized as a useful concept for this task, as the prediction power stems from the correlation, i.e., the mutual information, between features and labels. Many algorithms for feature selection in the literature have adopted the Shannon-entropy-based mutual information. In this paper, we explore the possibility of using Renyi min-entropy instead. In particular, we propose an algorithm based on a notion of conditional Renyi min-entropy that has been recently adopted in the field of security and privacy, and which is strictly related to the Bayes error. We prove that in general the two approaches are incomparable, in the sense that we show that we can construct datasets on which the Renyi-based algorithm performs better than the corresponding Shannon-based one, and datasets on which the situation is reversed. In practice, however, when considering datasets of real data, it seems that the Renyi-based algorithm tends to outperform the other one. We have effectuate several experiments on the BASEHOCK, SEMEION, and GISETTE datasets, and in all of them we have indeed observed that the Renyi-based algorithm gives better results.
We present a framework for analyzing the exact dynamics of a class of online learning algorithms in the high-dimensional scaling limit. Our results are applied to two concrete examples: online regularized linear regression and principal component analysis. As the ambient dimension tends to infinity, and with proper time scaling, we show that the time-varying joint empirical measures of the target feature vector and its estimates provided by the algorithms will converge weakly to a deterministic measured-valued process that can be characterized as the unique solution of a nonlinear PDE. Numerical solutions of this PDE can be efficiently obtained. These solutions lead to precise predictions of the performance of the algorithms, as many practical performance metrics are linear functionals of the joint empirical measures. In addition to characterizing the dynamic performance of online learning algorithms, our asymptotic analysis also provides useful insights. In particular, in the high-dimensional limit, and due to exchangeability, the original coupled dynamics associated with the algorithms will be asymptotically decoupled, with each coordinate independently solving a 1-D effective minimization problem via stochastic gradient descent. Exploiting this insight for nonconvex optimization problems may prove an interesting line of future research.
The predominant paradigm for using machine learning models on a device is to train a model in the cloud and perform inference using the trained model on the device. However, with increasing number of smart devices and improved hardware, there is interest in performing model training on the device. Given this surge in interest, a comprehensive survey of the field from a device-agnostic perspective sets the stage for both understanding the state-of-the-art and for identifying open challenges and future avenues of research. However, on-device learning is an expansive field with connections to a large number of related topics in AI and machine learning (including online learning, model adaptation, one/few-shot learning, etc.). Hence, covering such a large number of topics in a single survey is impractical. This survey finds a middle ground by reformulating the problem of on-device learning as resource constrained learning where the resources are compute and memory. This reformulation allows tools, techniques, and algorithms from a wide variety of research areas to be compared equitably. In addition to summarizing the state-of-the-art, the survey also identifies a number of challenges and next steps for both the algorithmic and theoretical aspects of on-device learning.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
