PyTorchKR Papers

최신 논문

총 568편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1805.09949공식 코드 · Papers with Code

Topological Data Analysis of Decision Boundaries with Application to Model Selection

We propose the labeled \v{C}ech complex, the plain labeled Vietoris-Rips complex, and the locally scaled labeled Vietoris-Rips complex to perform persistent homology inference of decision boundaries in classification tasks. We provide theoretical conditions and analysis for recovering the homology of a decision boundary from samples. Our main objective is quantification of deep neural network complexity to enable matching of datasets to pre-trained models; we report results for experiments using MNIST, FashionMNIST, and CIFAR10.

arXiv:1806.02034공식 코드 · Papers with Code

Degrees of Freedom and Model Selection for k-means Clustering

This paper investigates the model degrees of freedom in k-means clustering. An extension of Stein's lemma provides an expression for the effective degrees of freedom in the k-means model. Approximating the degrees of freedom in practice requires simplifications of this expression, however empirical studies evince the appropriateness of our proposed approach. The practical relevance of this new degrees of freedom formulation for k-means is demonstrated through model selection using the Bayesian Information Criterion. The reliability of this method is validated through experiments on simulated data as well as on a large collection of publicly available benchmark data sets from diverse application areas. Comparisons with popular existing techniques indicate that this approach is extremely competitive for selecting high quality clustering solutions. Code to implement the proposed approach is available in the form of an R package from https://github.com/DavidHofmeyr/edfkmeans.

arXiv:1802.07191공식 코드 · Papers with Code

Neural Architecture Search with Bayesian Optimisation and Optimal Transport

Bayesian Optimisation (BO) refers to a class of methods for global optimisation of a function $f$ which is only accessible via point evaluations. It is typically used in settings where $f$ is expensive to evaluate. A common use case for BO in machine learning is model selection, where it is not possible to analytically model the generalisation performance of a statistical model, and we resort to noisy and expensive training and validation procedures to choose the best model. Conventional BO methods have focused on Euclidean and categorical domains, which, in the context of model selection, only permits tuning scalar hyper-parameters of machine learning algorithms. However, with the surge of interest in deep learning, there is an increasing demand to tune neural network \emph{architectures}. In this work, we develop NASBOT, a Gaussian process based BO framework for neural architecture search. To accomplish this, we develop a distance metric in the space of neural network architectures which can be computed efficiently via an optimal transport program. This distance might be of independent interest to the deep learning community as it may find applications outside of BO. We demonstrate that NASBOT outperforms other alternatives for architecture search in several cross validation based model selection tasks on multi-layer perceptrons and convolutional neural networks.

arXiv:1804.05146공식 코드 · Papers with Code

A comparison of methods for model selection when estimating individual treatment effects

Practitioners in medicine, business, political science, and other fields are increasingly aware that decisions should be personalized to each patient, customer, or voter. A given treatment (e.g. a drug or advertisement) should be administered only to those who will respond most positively, and certainly not to those who will be harmed by it. Individual-level treatment effects can be estimated with tools adapted from machine learning, but different models can yield contradictory estimates. Unlike risk prediction models, however, treatment effect models cannot be easily evaluated against each other using a held-out test set because the true treatment effect itself is never directly observed. Besides outcome prediction accuracy, several metrics that can leverage held-out data to evaluate treatment effects models have been proposed, but they are not widely used. We provide a didactic framework that elucidates the relationships between the different approaches and compare them all using a variety of simulations of both randomized and observational data. Our results show that researchers estimating heterogenous treatment effects need not limit themselves to a single model-fitting algorithm. Instead of relying on a single method, multiple models fit by a diverse set of algorithms should be evaluated against each other using an objective function learned from the validation set. The model minimizing that objective should be used for estimating the individual treatment effect for future individuals.

arXiv:1806.05924공식 코드 · Papers with Code

Robust Bayesian Model Selection for Variable Clustering with the Gaussian Graphical Model

Variable clustering is important for explanatory analysis. However, only few dedicated methods for variable clustering with the Gaussian graphical model have been proposed. Even more severe, small insignificant partial correlations due to noise can dramatically change the clustering result when evaluating for example with the Bayesian Information Criteria (BIC). In this work, we try to address this issue by proposing a Bayesian model that accounts for negligible small, but not necessarily zero, partial correlations. Based on our model, we propose to evaluate a variable clustering result using the marginal likelihood. To address the intractable calculation of the marginal likelihood, we propose two solutions: one based on a variational approximation, and another based on MCMC. Experiments on simulated data shows that the proposed method is similarly accurate as BIC in the no noise setting, but considerably more accurate when there are noisy partial correlations. Furthermore, on real data the proposed method provides clustering results that are intuitively sensible, which is not always the case when using BIC or its extensions.

arXiv:2411.04440v1q-bio.QM공식 코드 · Papers with Code

AutoProteinEngine: A Large Language Model Driven Agent Framework for Multimodal AutoML in Protein Engineering

Protein engineering is important for biomedical applications, but conventional approaches are often inefficient and resource-intensive. While deep learning (DL) models have shown promise, their training or implementation into protein engineering remains challenging for biologists without specialized computational expertise. To address this gap, we propose AutoProteinEngine (AutoPE), an agent framework that leverages large language models (LLMs) for multimodal automated machine learning (AutoML) for protein engineering. AutoPE innovatively allows biologists without DL backgrounds to interact with DL models using natural language, lowering the entry barrier for protein engineering tasks. Our AutoPE uniquely integrates LLMs with AutoML to handle model selection for both protein sequence and graph modalities, automatic hyperparameter optimization, and automated data retrieval from protein databases. We evaluated AutoPE through two real-world protein engineering tasks, demonstrating substantial performance improvements compared to traditional zero-shot and manual fine-tuning approaches. By bridging the gap between DL and biologists' domain expertise, AutoPE empowers researchers to leverage DL without extensive programming knowledge. Our code is available at https://github.com/tsynbio/AutoPE.

arXiv:2410.07809v2cs.CL공식 코드 · Papers with Code

다국어 지시 미세조정에는 최적의 언어 집합이 존재하지 않는다: 언어학적 정보 기반 연구의 통찰

No Optimal Language Set Exists for Multilingual Instruction Tuning: Insights from a Linguistically-Informed Study

다국어 지시 미세조정(MIT)은 다국어의 저주, 데이터 부족, 높은 계산 비용으로 인해 어려움을 겪는다. 자연스러운 가설은 언어학적으로 다양한 언어 집합을 신중하게 선택하면 보편적으로 더 나은 모델을 얻을 수 있다는 것이다. 우리는 유형론적, 지리적, 의미적, 학습된 특징에 기반한 언어학적 정보 기반 선택 전략을 무작위 기준선과 비교 평가하여, 세 가지 모델 패밀리(mGPT, mT5-xl, BLOOM)와 다섯 개의 다국어 벤치마크에 걸쳐 이를 체계적으로 검증한다. 우리의 핵심적인 부정적 발견은 고정 예산 설정에서 보편적인 언어 선택 전략이 나타나지 않는다는 것이다. 성능은 작업과 모델에 크게 의존하며, 적당한 임계값을 넘어 더 많은 언어를 추가하면 다국어의 저주와 일치하는 성능 저하가 발생한다. MIT 데이터 큐레이션에 대한 함의와 벤치마크 평균 평가의 함정에 대해 논의한다. 모든 자료는 https://github.com/GGLAB-KU/ling-informed-mit 에서 공개적으로 이용할 수 있다.

arXiv:2404.10034v3cs.CV공식 코드 · Papers with Code

약지도 객체 위치 추정 평가를 위한 현실적인 프로토콜

A Realistic Protocol for Evaluation of Weakly Supervised Object Localization

약지도 객체 위치 추정(Weakly Supervised Object Localization, WSOL)은 전역 클래스 수준 레이블만을 사용하여 분류 및 위치 추정(LOC)을 위한 심층 학습 모델을 학습할 수 있게 한다. 학습 중 경계 상자(bounding box, bbox) 지도 정보의 부재는 하이퍼파라미터 튜닝, 모델 선택, 평가 측면에서 문헌상 여러 과제를 야기한다. WSOL 방법들은 모델 선택을 위해 경계 상자 어노테이션이 포함된 검증 세트에, 그리고 위치 추정 맵으로부터 경계 상자를 생성하기 위한 임계값 추정에 경계 상자 어노테이션이 포함된 테스트 세트에 의존한다. 그러나 이 접근 방식은 실제 환경에서 해당 어노테이션을 일반적으로 구할 수 없다는 점에서 WSOL 설정과 부합하지 않는다. 초기 실증 분석에서는 모델 선택과 임계값 추정을 각각 클래스 레이블과 이미지 자체에만 의존할 경우, 수동 경계 상자 어노테이션을 사용하는 경우에 비해 위치 추정 성능이 크게 저하됨을 확인하였다. 이는 최적의 모델 성능을 위해 경계 상자 레이블을 활용하는 것의 중요성을 강조한다. 본 논문에서는 수동 경계 상자 어노테이션 없이 위치 추정 정보를 제공하는 새로운 WSOL 평가 프로토콜을 제안한다. 구체적으로, Selective Search, CLIP, RPN과 같은 사전학습된 기성 영역 제안(region proposal) 방법으로부터 노이즈가 포함된 의사 경계 상자(pseudo-box)를 생성하여 모델 선택에 활용하였다. 이러한 경계 상자는 위치 추정 맵에서 임계값을 추정하는 데에도 사용되어 테스트 세트 경계 상자 어노테이션의 필요성을 우회한다. 도전적인 자연 이미지 및 의료 이미지 데이터셋에서 여러 WSOL 방법으로 수행한 실험 결과, 제안하는 의사 경계 상자를 검증에 활용하면 모델 선택과 임계값 추정이 용이해지며, 검증 세트에서 GT 경계 상자로 선택하고 테스트 세트에서 임계값을 추정한 모델과 비슷한 위치 추정 성능을 달성함을 보였다. 또한 클래스 수준 레이블로 선택한 후 위치 추정 맵만으로 동적 임계값을 적용한 모델보다 우수한 성능을 나타냈다.