Zobrazeno 1 - 10
of 1 466
pro vyhledávání: '"Farnia, P"'
Text-conditioned generation models are commonly evaluated based on the quality of the generated data and its alignment with the input text prompt. On the other hand, several applications of prompt-based generative models require sufficient diversity
Externí odkaz:
http://arxiv.org/abs/2411.02817
Autor:
Ospanov, Azim, Farnia, Farzan
Reference-free evaluation metrics for generative models have recently been studied in the machine learning community. As a reference-free metric, the VENDI score quantifies the diversity of generative models using matrix-based entropy from informatio
Externí odkaz:
http://arxiv.org/abs/2410.21719
In this paper, we address the challenge of certifying the performance of a machine learning model on an unseen target network, using measurements from an available source network. We focus on a scenario where heterogeneous datasets are distributed ac
Externí odkaz:
http://arxiv.org/abs/2410.20250
Selecting a sample generation scheme from multiple text-based generative models is typically addressed by choosing the model that maximizes an averaged evaluation score. However, this score-based selection overlooks the possibility that different mod
Externí odkaz:
http://arxiv.org/abs/2410.13287
Autor:
Goli, Hossein, Farnia, Farzan
A reliable application of deep neural network classifiers requires robustness certificates against adversarial perturbations. Gaussian smoothing is a widely analyzed approach to certifying robustness against norm-bounded perturbations, where the cert
Externí odkaz:
http://arxiv.org/abs/2409.13546
Autor:
Ospanov, Azim, Zhang, Jingwei, Jalali, Mohammad, Cao, Xuenan, Bogdanov, Andrej, Farnia, Farzan
While standard evaluation scores for generative models are mostly reference-based, a reference-dependent assessment of generative models could be generally difficult due to the unavailability of applicable reference datasets. Recently, the reference-
Externí odkaz:
http://arxiv.org/abs/2407.02961
Existing frameworks for evaluating and comparing generative models typically target an offline setting, where the evaluator has access to full batches of data produced by the models. However, in many practical scenarios, the goal is to identify the b
Externí odkaz:
http://arxiv.org/abs/2406.07451
Few-shot gradient methods have been extensively utilized in existing model pruning methods, where the model weights are regarded as static values and the effects of potential weight perturbations are not considered. However, the widely used large lan
Externí odkaz:
http://arxiv.org/abs/2406.07017
The Langevin Dynamics framework, which aims to generate samples from the score function of a probability distribution, is widely used for analyzing and interpreting score-based generative modeling. While the convergence behavior of Langevin Dynamics
Externí odkaz:
http://arxiv.org/abs/2406.02017
Autor:
Zhang, Jingwei, Farnia, Farzan
Transportation of samples across different domains is a central task in several machine learning problems. A sensible requirement for domain transfer tasks in computer vision and language domains is the sparsity of the transportation map, i.e., the t
Externí odkaz:
http://arxiv.org/abs/2405.07489