7 code implementations • Preprint 2019 • Nitish Shirish Keskar, Bryan McCann, Lav R. Varshney, Caiming Xiong, Richard Socher
Large-scale language models show promising text generation capabilities, but users cannot easily control particular aspects of the generated text.
2 code implementations • ICLR 2021 • Sourya Basu, Govardana Sachitanandam Ramachandran, Nitish Shirish Keskar, Lav R. Varshney
Experiments show that for low values of k and p in top-k and top-p sampling, perplexity drops significantly with generated text length, which is also correlated with excessive repetitions in the text (the boredom trap).
2 code implementations • ICLR 2021 • Jesse Vig, Ali Madani, Lav R. Varshney, Caiming Xiong, Richard Socher, Nazneen Fatema Rajani
Transformer architectures have proven to learn useful representations for protein classification and generation tasks.
1 code implementation • 5 Mar 2020 • Helena H. Lee, Ke Shu, Palakorn Achananuparp, Philips Kokoh Prasetyo, Yue Liu, Ee-Peng Lim, Lav R. Varshney
Interests in the automatic generation of cooking recipes have been growing steadily over the past few years thanks to a large amount of online cooking recipes.
1 code implementation • EMNLP 2020 • Samson Tan, Shafiq Joty, Lav R. Varshney, Min-Yen Kan
Inflectional variation is a common feature of World Englishes such as Colloquial Singapore English and African American Vernacular English.
1 code implementation • 7 Dec 2020 • Govardana Sachithanandam Ramachandran, Ivan Brugere, Lav R. Varshney, Caiming Xiong
Similarly, social networks within universities and organizations may enable certain groups to more easily access people with valuable information or influence.
1 code implementation • NeurIPS 2021 • Ryan Theisen, Huan Wang, Lav R. Varshney, Caiming Xiong, Richard Socher
Moreover, we show that by varying the temperature of the learned flow models, we can generate synthetic datasets that closely resemble standard benchmark datasets, but with almost any desired Bayes error.
1 code implementation • 10 Apr 2021 • Sourya Basu, Akshayaa Magesh, Harshit Yadav, Lav R. Varshney
We address these problems by proving a new group-theoretic result in the context of equivariant neural networks that shows that a network is equivariant to a large group if and only if it is equivariant to smaller groups from which it is constructed.
1 code implementation • 17 Sep 2019 • Helena Lee, Palakorn Achananuparp, Yue Liu, Ee-Peng Lim, Lav R. Varshney
Consumption of diets with low glycemic impact is highly recommended for diabetics and pre-diabetics as it helps maintain their blood glucose levels.
1 code implementation • 9 Apr 2018 • Sourya Basu, Lav R. Varshney
Deep neural networks have shown incredible performance for inference tasks in a variety of domains.
no code implementations • NeurIPS 2017 • Haizi Yu, Tianxi Li, Lav R. Varshney
Abstraction and realization are bilateral processes that are key in deriving intelligence and creativity.
no code implementations • 10 Jan 2017 • Ravi Kiran Raman, Lav R. Varshney
We consider the problem of universal joint clustering and registration of images and define algorithms using multivariate information functionals.
no code implementations • 6 May 2017 • Masahiro Kazama, Minami Sugimoto, Chizuru Hosokawa, Keisuke Matsushima, Lav R. Varshney, Yoshiki Ishikawa
We propose a novel system which can transform a recipe into any selected regional style (e. g., Japanese, Mediterranean, or Italian).
no code implementations • 17 Jun 2016 • Haizi Yu, Lav R. Varshney, Guy E. Garnett, Ranjitha Kumar
Throughout music history, theorists have identified and documented interpretable rules that capture the decisions of composers.
no code implementations • 1 Feb 2016 • Qunwei Li, Aditya Vempaty, Lav R. Varshney, Pramod K. Varshney
We present an aggregation approach using a weighted majority voting rule, where each worker's response is assigned an optimized weight to maximize the crowd's classification performance.
no code implementations • 13 Mar 2014 • Amin Karbasi, Amir Hesam Salavati, Amin Shokrollahi, Lav R. Varshney
More surprisingly, we show that internal noise actually improves the performance of the recall phase while the pattern retrieval capacity remains intact, i. e., the number of stored patterns does not reduce with noise (up to a threshold).
1 code implementation • 5 Nov 2013 • Lav R. Varshney, Florian Pinel, Kush R. Varshney, Debarun Bhattacharjya, Angela Schoergendorfer, Yi-Min Chee
Computational creativity is an emerging branch of artificial intelligence that places computers in the center of the creative process.
no code implementations • 30 Jul 2018 • Haizi Yu, Igor Mineyev, Lav R. Varshney
Abstraction plays a key role in concept learning and knowledge discovery; this paper is concerned with computational abstraction.
no code implementations • NeurIPS 2013 • Amin Karbasi, Amir Hesam Salavati, Amin Shokrollahi, Lav R. Varshney
More surprisingly, we show that internal noise actually improves the performance of the recall phase.
no code implementations • NeurIPS 2011 • Alyson K. Fletcher, Sundeep Rangan, Lav R. Varshney, Aniruddha Bhargava
Many functional descriptions of spiking neurons assume a cascade structure where inputs are passed through an initial linear filtering stage that produces a low-dimensional signal that drives subsequent nonlinear stages.
no code implementations • 9 May 2019 • Sakshi Agarwal, Lav R. Varshney
Deepfake detection is formulated as a hypothesis testing problem to classify an image as genuine or GAN-generated.
no code implementations • 20 May 2019 • Xiou Ge, Richard T. Goodwin, Jeremy R. Gregory, Randolph E. Kirchain, Joana Maria, Lav R. Varshney
Concrete is the most widely used engineered material in the world with more than 10 billion tons produced annually.
no code implementations • 23 Nov 2018 • Daewon Seo, Ravi Kiran Raman, Joong Bum Rhim, Vivek K Goyal, Lav R. Varshney
In addition, the agents have their own beliefs instead of the true prior, and have nonidentical noise variances in the private signal.
no code implementations • 27 Aug 2019 • Huozhi Zhou, Lingda Wang, Lav R. Varshney, Ee-Peng Lim
Compared to the original combinatorial semi-bandit problem, our setting assumes the reward distributions of base arms may change in a piecewise-stationary manner at unknown time steps.
no code implementations • 7 Sep 2019 • Lav R. Varshney, Nitish Shirish Keskar, Richard Socher
The paradigm of pretrained deep learning models has recently emerged in artificial intelligence practice, allowing deployment in numerous societal settings with limited computational resources, but also embedding biases and enabling unintended negative uses.
no code implementations • 10 Sep 2019 • Yongjune Kim, Yuval Cassuto, Lav R. Varshney
Suppose that the base classifiers' outputs are noisy or communicated over noisy channels; these noisy outputs will degrade the final classification accuracy.
no code implementations • 12 Sep 2019 • Lingda Wang, Huozhi Zhou, Bingcong Li, Lav R. Varshney, Zhizhen Zhao
Cascading bandit (CB) is a popular model for web search and online advertising, where an agent aims to learn the $K$ most attractive items out of a ground set of size $L$ during the interaction with a user.
no code implementations • 1 Nov 2019 • Lavanya Marla, Lav R. Varshney, Devavrat Shah, Nirmal A. Prakash, Michael E. Gale
We show this notion of pipelined network flow is optimized using network paths that are both short and wide, and develop efficient algorithms to compute such paths for given pairs of nodes and for all-pairs.
no code implementations • 9 Feb 2020 • Lav R. Varshney, Nitish Shirish Keskar, Richard Socher
Some consider large-scale language models that can generate long and coherent pieces of text as dangerous, since they may be used in misinformation campaigns.
no code implementations • 15 Apr 2020 • Haizi Yu, Heinrich Taube, James A. Evans, Lav R. Varshney
Interpretability of machine learning models has gained more and more attention among researchers in the artificial intelligence (AI) and human-computer interaction (HCI) communities.
no code implementations • 17 Sep 2020 • Pushpendra Rana, Lav R. Varshney
Large-scale planting of trees has been proposed as a low-cost natural solution for carbon mitigation, but is hampered by poor selection of plantation sites, especially in developing countries.
no code implementations • 1 Jan 2021 • Haizi Yu, James Evans, Lav R. Varshney
ILL focuses on explainability and generalizability from "small data", and aims for rules akin to those humans distill from experience (rather than a representation optimized for a specific task like classification).
no code implementations • 8 Oct 2020 • Huozhi Zhou, Jinglin Chen, Lav R. Varshney, Ashish Jagmohan
We consider reinforcement learning (RL) in episodic Markov decision processes (MDPs) with linear function approximation under drifting environment.
no code implementations • 14 Oct 2020 • Lav R. Varshney, Nazneen Fatema Rajani, Richard Socher
Human creativity is often described as the mental process of combining associative elements into a new form, but emerging computational creativity algorithms may not operate in this manner.
no code implementations • 21 Oct 2020 • Sam Spencer, Lav R. Varshney
Previous work has shown that for contagion processes on extended star networks (trees with exactly one node of degree > 2), there is a simple, closed-form expression for a highly accurate approximation to the maximum likelihood infection source.
no code implementations • 10 Dec 2020 • Lingda Wang, Bingcong Li, Huozhi Zhou, Georgios B. Giannakis, Lav R. Varshney, Zhizhen Zhao
The second algorithm, \texttt{EXP3-LGC-IX}, is developed for a special class of problems, for which the regret is reduced to $\mathcal{O}(\sqrt{\alpha(G)dT\log{K}\log(KT)})$ for both directed as well as undirected feedback graphs.
no code implementations • 8 Nov 2020 • Taha Ameen ur Rahman, Alton S. Barbehenn, Xinan Chen, Hassan Dbouk, James A. Douglas, Yuncong Geng, Ian George, John B. Harvill, Sung Woo Jeon, Kartik K. Kansal, Kiwook Lee, Kelly A. Levick, Bochao Li, Ziyue Li, Yashaswini Murthy, Adarsh Muthuveeru-Subramaniam, S. Yagiz Olmez, Matthew J. Tomei, Tanya Veeravalli, Xuechao Wang, Eric A. Wayman, Fan Wu, Peng Xu, Shen Yan, Heling Zhang, Yibo Zhang, Yifan Zhang, Yibo Zhao, Sourya Basu, Lav R. Varshney
Many information sources are not just sequences of distinguishable symbols but rather have invariances governed by alternative counting paradigms such as permutations, combinations, and partitions.
Information Theory Information Theory
1 code implementation • NIPS Workshop CDNNRIA 2018 • Sourya Basu, Lav R. Varshney
Deep neural networks have shown incredible performance for inference tasks in a variety of domains.
no code implementations • 14 Jan 2022 • Haizi Yu, Igor Mineyev, Lav R. Varshney, James A. Evans
Using simply the nearest-neighbor classifier on this similarity space, we achieve human-level character recognition using only 1--10 examples per class and nothing else (no pre-training).
no code implementations • NeurIPS Workshop AI4Scien 2021 • Evan D. Anderson, Ramsey Wilcox, Anuj Nayak, Christopher Zwilling, Pablo Robles-Granda, Been Kim, Lav R. Varshney, Aron K. Barbey
Investigating the proposed modeling framework's efficacy, we find that advanced connectome-based predictive modeling generates neuroscience predictions that account for a significantly greater proportion of variance in general intelligence scores than previously established methods, advancing our scientific understanding of the network architecture that underlies human intelligence.
no code implementations • 11 Apr 2022 • Xiou Ge, Richard T. Goodwin, Haizi Yu, Pablo Romero, Omar Abdelrahman, Amruta Sudhalkar, Julius Kusuma, Ryan Cialdella, Nishant Garg, Lav R. Varshney
Finally, we report on how these formulations were used in the construction of buildings and structures in a Meta data center in DeKalb, IL, USA.
no code implementations • 8 Aug 2022 • Babak Hemmatian, Lav R. Varshney
Recent work demonstrates a bias in the GPT-3 model towards generating violent text completions when prompted about Muslims, compared with Christians and Hindus.
no code implementations • 13 Oct 2022 • Sourya Basu, Prasanna Sattigeri, Karthikeyan Natesan Ramamurthy, Vijil Chenthamarakshan, Kush R. Varshney, Lav R. Varshney, Payel Das
We also provide a novel group-theoretic definition for fairness in NLG.
1 code implementation • 28 Jan 2023 • Moulik Choraria, Ibtihal Ferwana, Ankur Mani, Lav R. Varshney
Learning models that are robust to distribution shifts is a key concern in the context of their real-life applicability.
no code implementations • 15 May 2023 • Ibtihal Ferwana, Suyoung Park, Ting-Yi Wu, Lav R. Varshney
To do so, we propose a quantization-theoretic approach to optimize the effect of interest, first learning the causal effect size of a given discontinuous variable and then applying dynamic programming for optimal quantization design of discontinuities to balance the gain and loss in that effect size.
no code implementations • 15 Jul 2023 • Sourya Basu, Moulik Choraria, Lav R. Varshney
We find limits to the Transformer architecture for language modeling and show it has a universal prediction property in an information-theoretic sense.
no code implementations • 9 Oct 2023 • Xinbo Wu, Lav R. Varshney
Focused on the training process, here we establish a meta-learning view of the Transformer architecture when trained for the causal language modeling task, by explicating an inner optimization process within the Transformer.
no code implementations • 14 Oct 2023 • Razan Baltaji, Sourya Basu, Lav R. Varshney
Inspired by the first design, we use the notion of the IS property to design a second efficient model-agnostic equivariant design for large product groups acting on a single input.
no code implementations • 25 Oct 2023 • Babak Hemmatian, Razan Baltaji, Lav R. Varshney
Abid et al. (2021) showed a tendency in GPT-3 to generate mostly violent completions when prompted about Muslims, compared with other religions.
no code implementations • 13 Nov 2023 • Moulik Choraria, Nitesh Sekhar, Yue Wu, Xu Zhang, Prateek Singhal, Lav R. Varshney
Large-scale pretraining and instruction tuning have been successful for training general-purpose language models with broad competencies.
no code implementations • 19 Feb 2024 • Xinbo Wu, Lav R. Varshney
Even though large language models (LLMs) have demonstrated remarkable capability in solving various natural language tasks, the capability of an LLM to follow human instructions is still a concern.
no code implementations • 1 Mar 2024 • Seyed Mohammad Azimi-Abarghouyi, Lav R. Varshney
This paper introduces a universal federated learning framework that enables over-the-air computation via digital communications, using a new joint source-channel coding scheme.