paper-with-me

Papers

Convergence to the Truth

2024-10-15 · Hanti Lin

This article reviews and develops an epistemological tradition in the philosophy of science, known as convergentism, which holds that inference methods should be assessed based on their ability to converge to the truth across a range of possible scenarios. Emphasis is placed on its historical origins in the work of C. S. Peirce and its recent developments in formal epistemology and data science (including statistics and machine learning). Comparisons are made with three other traditions: (1) explanationism, which holds that theory choice should be guided by a theory's overall balance of explanatory virtues, such as simplicity and fit with data; (2) instrumentalism, which maintains that scientific inference should be driven by the goal of obtaining useful models rather than true theories; and (3) Bayesianism, which shifts the focus from all-or-nothing beliefs to degrees of belief.

📄 PDF Abstract BibTeX arXiv:2410.11399

Code (0)

등록된 구현이 없습니다.

Tasks

Philosophy

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Global Convergence of Gradient EM for Over-Parameterized Gaussian Mixtures

2025-06-06 · Mo Zhou, Weihang Xu, Maryam Fazel, Simon S. Du arxiv

Learning Gaussian Mixture Models (GMMs) is a fundamental problem in statistics and machine learning, with the Expectation-Maximization (EM) algorithm and its popular variant gradient EM being arguably the most widely use…

Convergence Dynamics of Over-Parameterized Score Matching for a Single Gaussian

2025-11-27 · Yiran Zhang, Weihang Xu, Mo Zhou, Maryam Fazel 외 arxiv

Score matching has become a central training objective in modern generative modeling, particularly in diffusion models, where it is used to learn high-dimensional data distributions through the estimation of score functi…

Gradient Manipulation in Distributed Stochastic Gradient Descent with Strategic Agents: Truthful Incentives with Convergence Guarantees

2026-03-30 · Ziqin Chen, Yongqiang Wang arxiv

Distributed learning has gained significant attention due to its advantages in scalability, privacy, and fault tolerance.In this paradigm, multiple agents collaboratively train a global model by exchanging parameters onl…

Hypothesis Testing in Feedforward Networks with Broadcast Failures

2012-11-19 · Zhenliang Zhang, Edwin K. P. Chong, Ali Pezeshki, William Moran

Consider a countably infinite set of nodes, which sequentially make decisions between two given hypotheses. Each node takes a measurement of the underlying truth, observes the decisions from some immediate predecessors, …

Two-sample testing

HyperNet Fields: Efficiently Training Hypernetworks without Ground Truth by Learning Weight Trajectories

2024-12-22 · CVPR 2025 1 · Eric Hedlin, Munawar Hayat, Fatih Porikli, Kwang Moo Yi 외

To efficiently adapt large models or to train generative models of neural representations, Hypernetworks have drawn interest. While hypernetworks work well, training them is cumbersome, and often requires ground truth op…

3D Shape ReconstructionImage GenerationPersonalized Image Generation