Shashank Srikant

Shashank Srikant

Auto-generated profile, based on publicly available information

Shashank Srikant

Computer Science & Artificial Intelligence Laboratory, Massachusetts Institute of Technology

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 August 2016
Verified
Conference Paper
Open access
PDF file
GSGursimran Singh
Gursimran Singh
SSShashank Srikant
Shashank Srikant
VAVarun Aggarwal
Varun Aggarwal
Learning supervised models to grade open-ended responses is an expensive process. A model has to be trained for every prompt/question separately, which in turn requires graded samples. In automatic programming evaluation specifically, the focus of this work, this issue is amplified. The models have to be trained not only for every question but also for every language the question is offered in. Moreover, the availability and time taken by experts to create a labeled set of programs for each question is a major bottleneck in scaling such a system. We address this issue by presenting a method to grade computer programs which requires no manually assigned labeled samples for grading responses to a new, unseen question. We extend our previous work [25] wherein we introduced a grammar of features to learn question specific models. In this work, we propose a method to transform those features into a set of features that maintain their structural relation with the labels across questions. Using these features we learn one supervised model, across questions for a given language, which can then be applied to an ungraded response to an unseen question. We show that our method rivals the performance of both, question specific models and the consensus among human experts while substantially outperforming extant ways of evaluating codes. We demonstrate the system single s value by deploying it to grade programs in a high stakes assessment. The learning from this work is transferable to other grading tasks such as math question grading and also provides a new variation to the supervised learning approach.

12 February 2019 in AIP Conference Proceedings
Verified
Conference Paper
Open access
PDF file
AAAbdullah Al-Dujaili
Abdullah Al-Dujaili
SSShashank Srikant
Shashank Srikant
EHErik Hemberg
Erik Hemberg
UOUna-May O’reilly
Una-May O’reilly
Motivated by Danskin’s theorem, gradient-based methods have been applied with empirical success to solve minimax problems that involve non-convex outer minimization and non-concave inner maximization. On the other hand, recent work has demonstrated that Evolution Strategies (ES) algorithms are stochastic gradient approximators that seek robust solutions. In this paper, we address black-box (gradient-free) minimax problems that have long been tackled in a coevolutionary setup. To this end and guaranteed by Danskin’s theorem, we employ ES as a stochastic estimator for descent directions. The proposed approach is validated on a collection of black-box minimax problems. Based on our experiments, our method’s performance is comparable with its coevolutionary counterparts and favorable for high-dimensional problems. Its efficacy is demonstrated on a real-world application.

16 April 2023 in bioRxiv
Verified
Preprint
Open access
PDF file
GTGreta Tuckute
Greta Tuckute
ASAalok Sathe
Aalok Sathe
SSShashank Srikant
Shashank Srikant
MTMaya Taliaferro
Maya Taliaferro
MWMingye Wang
Mingye Wang
EFEvelina Fedorenko
Evelina Fedorenko
Transformer models such as GPT generate human-like language and are highly predictive of human brain responses to language. Here, using fMRI-measured brain responses to 1,000 diverse sentences, we first show that a GPT-based encoding model can predict the magnitude of brain response associated with each sentence. Then, we use the model to identify new sentences that are predicted to drive or suppress responses in the human language network. We show that these model-selected novel sentences indeed strongly drive and suppress activity of human language areas in new individuals. A systematic analysis of the model-selected sentences reveals that surprisal and well-formedness of linguistic input are key determinants of response strength in the language network. These results establish the ability of neural network models to not only mimic human language but also noninvasively control neural activity in higher-level cortical areas, like the language network.

3 March 2023 in arXiv
Verified
Preprint
Open access
PDF file
JJJinghan Jia
Jinghan Jia
SSShashank Srikant
Shashank Srikant
TMTamara Mitrovska
Tamara Mitrovska
CGChuang Gan
Chuang Gan
SCShiyu Chang
Shiyu Chang
UOUna-May O'Reilly
Una-May O'Reilly
We integrate contrastive learning (CL) with adversarial learning to co-optimize the robustness and accuracy of code models. Different from existing works, we show that code obfuscation, a standard code transformation operation, provides novel means to generate complementary `views' of a code that enable us to achieve both robust and accurate code models. To the best of our knowledge, this is the first systematic study to explore and exploit the robustness and accuracy benefits of (multi-view) code obfuscations in code models. Specifically, we first adopt adversarial codes as robustness-promoting views in CL at the self-supervised pre-training phase. This yields improved robustness and transferability for downstream tasks. Next, at the supervised fine-tuning stage, we show that adversarial training with a proper temporally-staggered schedule of adversarial code generation can further improve robustness and accuracy of the pre-trained code model. Built on the above two modules, we develop CLAWSAT, a novel self-supervised learning (SSL) framework for code by integrating $\underline{\textrm{CL}}$ with $\underline{\textrm{a}}$dversarial vie$\underline{\textrm{w}}$s (CLAW) with $\underline{\textrm{s}}$taggered $\underline{\textrm{a}}$dversarial $\underline{\textrm{t}}$raining (SAT). On evaluating three downstream tasks across Python and Java, we show that CLAWSAT consistently yields the best robustness and accuracy ($\textit{e.g.}$ 11$\%$ in robustness and 6$\%$ in accuracy on the code summarization task in Python). We additionally demonstrate the effectiveness of adversarial learning in CLAW by analyzing the characteristics of the loss landscape and interpretability of the pre-trained models.