Zobrazeno 1 - 10
of 191
pro vyhledávání: '"Koyejo, Oluwasanmi"'
Probabilistic generative models of graphs are important tools that enable representation and sampling. Many recent works have created probabilistic models of graphs that are capable of representing not only entity interactions but also their attribut
Externí odkaz:
http://arxiv.org/abs/2308.03773
Autor:
Robertson, Zachary, Koyejo, Oluwasanmi
Feedback Alignment (FA) methods are biologically inspired local learning rules for training neural networks with reduced communication between layers. While FA has potential applications in distributed and privacy-aware ML, limitations in multi-class
Externí odkaz:
http://arxiv.org/abs/2306.01870
Autor:
Robertson, Zachary, Koyejo, Oluwasanmi
The growing demand for data and AI-generated digital goods, such as personalized written content and artwork, necessitates effective pricing and feedback mechanisms that account for uncertain utility and costly production. Motivated by these developm
Externí odkaz:
http://arxiv.org/abs/2306.01860
Autor:
Schaeffer, Rylan, Khona, Mikail, Robertson, Zachary, Boopathy, Akhilan, Pistunova, Kateryna, Rocks, Jason W., Fiete, Ila Rani, Koyejo, Oluwasanmi
Double descent is a surprising phenomenon in machine learning, in which as the number of model parameters grows relative to the number of data, test error drops as models grow ever larger into the highly overparameterized (data undersampled) regime.
Externí odkaz:
http://arxiv.org/abs/2303.14151
Autor:
Salaudeen, Olawale, Koyejo, Oluwasanmi
We propose a Target Conditioned Representation Independence (TCRI) objective for domain generalization. TCRI addresses the limitations of existing domain generalization methods due to incomplete constraints. Specifically, TCRI implements regularizers
Externí odkaz:
http://arxiv.org/abs/2212.11342
Metric Elicitation (ME) is a framework for eliciting classification metrics that better align with implicit user preferences based on the task and context. The existing ME strategy so far is based on the assumption that users can most easily provide
Externí odkaz:
http://arxiv.org/abs/2212.03495
Active learning enables efficient model training by leveraging interactions between machine learning agents and human annotators. We study and propose a novel framework that formulates batch active learning from the sparse approximation's perspective
Externí odkaz:
http://arxiv.org/abs/2211.00246
Recent work on 3D-aware image synthesis has achieved compelling results using advances in neural rendering. However, 3D-aware synthesis of face dynamics hasn't received much attention. Here, we study how to explicitly control generative model synthes
Externí odkaz:
http://arxiv.org/abs/2210.05825
In the experimental sciences, statistical power analyses are often used before data collection to determine the required sample size. However, traditional power analyses can be costly when data are difficult or expensive to collect. We propose synthe
Externí odkaz:
http://arxiv.org/abs/2210.05835
Publikováno v:
In Neural Information Processing Systems (NeurIPS), 2022
We propose a novel reduction-to-binary (R2B) approach that enforces demographic parity for multiclass classification with non-binary sensitive attributes via a reduction to a sequence of binary debiasing tasks. We prove that R2B satisfies optimality
Externí odkaz:
http://arxiv.org/abs/2205.15860