Prof. at UTD CS, Director @caraml_lab | ML/AI/Optimization | Ex-Microsoft | MS, PhD: UW, BTech: IITB | https://xitter.gq/t.co/TB3cpJcBeC
Dallas, TX
Joined February 2016
- Tweets561
- Following332
- Followers1.6K
- Likes1.8K
Rishabh Iyer retweeted
What makes a dataset valuable? And when is "more data" not the same as "better data" in machine learning and AI? Read more to find out: arxiv.org/abs/2605.29448
Rishabh Iyer retweeted
Please congragulate my dear friend @Sriraam_UTD who is now a AAAI fellow. Well done @Sriraam_UTD .
Details here: aaai.org/about-aaai/aaai-awa…
Rishabh Iyer retweeted
Day 1: Session 2 Machine Learning
Talk 2: Rishabh Iyer Professor UT Dallas
Subset Selection for Compute-Efficient Deep Learning
Professor Rishabh took us through approaches like GLISTER, GRAD-MATCH, MILD, which helped us make our concepts on subset selection crystal clear!
Rishabh Iyer retweeted
Our work, in collaboration with Prof. Abir De of IIT Bombay, @eeshaan_jain, @rishiyer and @fooobar, on Learning to Select a Subset of Training Examples to Generalize Efficient Model Training has been accepted at #NeurIPS 2023. (1/n)
Rishabh Iyer retweeted
India's successful lunar mission (landing its Chandrayaan-3 spacecraft on the moon) is another one of many straws in the wind showing its ascendence. As previously shown in my health index for countries, which is used to derive my projections for countries' next 10-year growth rates, India scores on top with a projected growth rate over the next 10 years of about 7%. It has the right mix of ingredients that shows that it has great potential and the right leadership to catalyze it. It reminds me a lot of China in 1984 (when I first went) around the time Deng Xiaoping made his reform and opening up policies that catalyzed China. Congratulations India!
Rishabh Iyer retweeted
Prof. Abir De and Prof. Rishabh Iyer @rishiyer giving a Tutorial on "Coresets and Combinatorial Optimization for Efficient and Robust Deep Learning" at #IndoML2022
#IndoML #IITGN @cse_iitgn @iitgn – at Gandhinagar, India
Rishabh Iyer retweeted
Happy to share that our paper titled "Partitioned Gradient Matching based Data Subset Selection
for Compute-Efficient & Robust ASR Training" has been accepted to EMNLP 2022 (findings). This is joint work with Durga S, @rishiyer @PreethiJyothi1 and @ganramkr.
Rishabh Iyer retweeted
📢 Trying to tackle class imbalance and out-of-distribution(OOD) scenarios in medical imaging? #MICCAI2022
Obtaining labeled medical data is difficult and expensive since it requires expert annotators like doctors; such imperfections in data exponentiate this difficulty.
1/n
Rishabh Iyer retweeted
Want to build a text classifier in a few hours?
Even if you don’t have any:
labeled data
#machineLearning knowledge
programing skills
Label Sleuth ibm.biz/label-sleuth a new open-source no-code system for annotations 🧵 @IBMResearch @NotreDame @StanfordHCI UT Dallas #NLProc
Rishabh Iyer retweeted
📢 Finding it difficult to meta-learn models for Few-shot classification tasks? #ICML2022
We present PLATINUM: Semi-Supervised Model Agnostic Meta-Learning using Submodular Mutual Information accepted to ICML 2022!
📰 Paper: arxiv.org/pdf/2201.12928.pdf
Rishabh Iyer retweeted
📢Trying to improve your object detection models but see them consistently failing on the same kind of scenarios? #ECCV2022
We present TALISMAN: Targeted Active Learning for Object Detection with Rare Classes and Slices using Submodular Mutual Information, accepted to ECCV 2022!
Rishabh Iyer retweeted
I am thrilled to announce that my 3-minute pitch based on my dissertation titled "Data Exploration and Targeted Learning" was awarded the runner-up at the 3-Minute-Thesis (3MT) competition hosted by the University of Texas at Dallas @UTDOGE.
Rishabh Iyer retweeted
I am beyond excited to announce that "Optimization for Data Analysis," by @madsjw and myself, has been published by @CambridgeUP.
cambridge.org/us/academic/su…
Rishabh Iyer retweeted
A solid point!👇🏼
A lot of focus in AI/ML is towards building the (n+1)th model, while there is little work on techniques to improve models that already exists.
In my opinion there are two important practical questions that need to be addressed to bridge this GAP.
Rishabh Iyer retweeted
I wish research papers have a section in the appendix that is titled - "What did not work".
Although the main paper should outline "what works", it's worth writing about the series of failed experiments.
Rishabh Iyer retweeted
I'm excited to present PRISM at #AAAI2022
Please stop by our Poster Sessions:
🗓️Feb 25, 4:45PM - 6:30PM PST
🗓️Feb 27, 8:45AM - 10:30AM PST
Poster Session 5,10@Blue 2
aaai-2022.virtualchair.net/p…
📢Looking for data subset selection functions that can be customized as per your requirements? #AAAI2022
We present PRISM: A Rich Class of Parameterized Submodular Information Measures for Guided Subset Selection
📰Paper : arxiv.org/pdf/2103.00128.pdf
1/N
Rishabh Iyer retweeted
Prof. @rishiyer compares and contrasts between Tenure-track/tenured position, Research Labs, Industry Labs and Startups. Points on Research Lab and Industry Lab was new to me.
Academia vs Industry: A Twelve Point Comparison youtu.be/H6wSxSXkr1w via @YouTube
Rishabh Iyer retweeted
Because of the "Github, Notebook and Blog culture". People are overrating code so much and ignoring the fundamental principle let alone math.