no code implementations • 5 Dec 2024 • Ali Abbasi, Shima Imani, Chenyang An, Gayathri Mahalingam, Harsh Shrivastava, Maurice Diesendruck, Hamed Pirsiavash, Pramod Sharma, Soheil Kolouri
Next, we leverage a generative foundation model to dynamically expand this compressed set in real-time, enhancing the resolution of these patches and introducing controlled variability to the coreset.
1 code implementation • 19 Feb 2024 • Harsh Shrivastava
In other words, the neural networks learn a many-to-one mapping and this effect is more prominent as we increase the number of layers or the depth of the neural network.
no code implementations • 20 Sep 2023 • Urszula Chajewska, Harsh Shrivastava
We develop a FL framework which maintains a global NGM model that learns the averaged information from the local NGM models while keeping the training data within the client's environment.
no code implementations • 10 Aug 2023 • Urszula Chajewska, Harsh Shrivastava
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.
no code implementations • 22 Jun 2023 • Shima Imani, Ali Beyram, Harsh Shrivastava
In this paper, we introduce DiversiGATE, a unified framework that consolidates diverse methodologies for LLM verification.
1 code implementation • 21 Mar 2023 • Shima Imani, Harsh Shrivastava
Segmentation of multivariate time series data is a technique for identifying meaningful patterns or changes in the time series that can signal a shift in the system's behavior.
1 code implementation • 4 Mar 2023 • Shima Imani, Liang Du, Harsh Shrivastava
Large Language Models (LLMs) have limited performance when solving arithmetic reasoning tasks and often provide incorrect answers.
1 code implementation • 27 Feb 2023 • Harsh Shrivastava, Urszula Chajewska
Sparse graph recovery methods work well where the data follows their assumptions but often they are not designed for doing downstream probabilistic queries.
1 code implementation • 13 Nov 2022 • Harsh Shrivastava, Urszula Chajewska
Conditional Independence (CI) graphs are a type of probabilistic graphical models that are primarily used to gain insights about feature relationships.
2 code implementations • 2 Oct 2022 • Harsh Shrivastava, Urszula Chajewska
Theoretically these models can represent very complex dependency functions, but in practice often simplifying assumptions are made due to computational limitations associated with graph operations.
4 code implementations • 23 May 2022 • Harsh Shrivastava, Urszula Chajewska, Robin Abraham, Xinshi Chen
Our model, uGLAD, builds upon and extends the state-of-the-art model GLAD to the unsupervised setting.
no code implementations • 18 Feb 2021 • Harsh Shrivastava, Ankush Garg, Yuan Cao, Yu Zhang, Tara Sainath
We propose automatic speech recognition (ASR) models inspired by echo state network (ESN), in which a subset of recurrent neural networks (RNN) layers in the models are randomly initialized and untrained.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
no code implementations • 1 Jan 2021 • Gaurav Shrivastava, Harsh Shrivastava, Abhinav Shrivastava
But, what if for an input point '$\bar{\mathbf{x}}$', we want to constrain the GP to avoid a target regression value '$\bar{y}(\bar{\mathbf{x}})$' (a negative datapair)?
no code implementations • ICLR 2019 • Samyam Rajbhandari, Harsh Shrivastava, Yuxiong He
Wide adoption of complex RNN based models is hindered by their inference performance, cost and memory requirements.
1 code implementation • ICLR 2020 • Harsh Shrivastava, Xinshi Chen, Binghong Chen, Guanghui Lan, Srinvas Aluru, Han Liu, Le Song
Recently, there is a surge of interest to learn algorithms directly based on data, and in this case, learn to map empirical covariance to the sparse precision matrix.
no code implementations • NeurIPS 2018 • Harsh Shrivastava, Eugene Bart, Bob Price, Hanjun Dai, Bo Dai, Srinivas Aluru
We propose a new approach, called cooperative neural networks (CoNN), which uses a set of cooperatively trained neural networks to capture latent representations that exploit prior given independence structure.