Zobrazeno 1 - 10
of 38
pro vyhledávání: '"Shrivastava, Harsh"'
Autor:
Shrivastava, Harsh
We discovered that the neural networks, especially the deep ReLU networks, demonstrate an `over-generalization' phenomenon. That is, the output values for the inputs that were not seen during training are mapped close to the output range that were ob
Externí odkaz:
http://arxiv.org/abs/2402.11793
Autor:
Chajewska, Urszula, Shrivastava, Harsh
Federated Learning (FL) addresses the need to create models based on proprietary data in such a way that multiple clients retain exclusive control over their data, while all benefit from improved model accuracy due to pooled resources. Recently propo
Externí odkaz:
http://arxiv.org/abs/2309.11680
Autor:
Chajewska, Urszula, Shrivastava, Harsh
Conditional Independence (CI) graph is a special type of a Probabilistic Graphical Model (PGM) where the feature connections are modeled using an undirected graph and the edge weights show the partial correlation strength between the features. Since
Externí odkaz:
http://arxiv.org/abs/2308.05857
In this paper, we introduce DiversiGATE, a unified framework that consolidates diverse methodologies for LLM verification. The proposed framework comprises two main components: Diversification and Aggregation which provide a holistic perspective on e
Externí odkaz:
http://arxiv.org/abs/2306.13230
Autor:
Imani, Shima, Shrivastava, Harsh
We frequently encounter multiple series that are temporally correlated in our surroundings, such as EEG data to examine alterations in brain activity or sensors to monitor body movements. Segmentation of multivariate time series data is a technique f
Externí odkaz:
http://arxiv.org/abs/2303.11647
Large Language Models (LLMs) have limited performance when solving arithmetic reasoning tasks and often provide incorrect answers. Unlike natural language understanding, math problems typically have a single correct answer, making the task of generat
Externí odkaz:
http://arxiv.org/abs/2303.05398
Autor:
Shrivastava, Harsh, Chajewska, Urszula
Sparse graph recovery methods work well where the data follows their assumptions but often they are not designed for doing downstream probabilistic queries. This limits their adoption to only identifying connections among the input variables. On the
Externí odkaz:
http://arxiv.org/abs/2302.13582
Autor:
Shrivastava, Harsh, Chajewska, Urszula
Publikováno v:
Journal of Artificial Intelligence Research 80 (2024) 593-612
Conditional Independence (CI) graphs are a type of probabilistic graphical models that are primarily used to gain insights about feature relationships. Each edge represents the partial correlation between the connected features which gives informatio
Externí odkaz:
http://arxiv.org/abs/2211.06829
Autor:
Shrivastava, Harsh, Chajewska, Urszula
Probabilistic Graphical Models are often used to understand dynamics of a system. They can model relationships between features (nodes) and the underlying distribution. Theoretically these models can represent very complex dependency functions, but i
Externí odkaz:
http://arxiv.org/abs/2210.00453
Probabilistic Graphical Models (PGMs) are generative models of complex systems. They rely on conditional independence assumptions between variables to learn sparse representations which can be visualized in a form of a graph. Such models are used for
Externí odkaz:
http://arxiv.org/abs/2205.11610