196 citations · 394 across the 27 of their papers we have counts for
29 papers
Uncovering Drift in Textual Data: An Unsupervised Method for Detecting and Mitigating Drift in Machine Learning Models
Saeed Khaki, Akhouri Abhinav Aditya, Zohar Karnin +3
Drift in machine learning refers to the phenomenon where the statistical properties of data or context, in which the model operates, change over time leading to a decrease in its p…
Representation Projection Invariance Mitigates Representation Collapse
Anastasia Razdaibiedina, Ashish Khetan, Zohar Karnin +3
Fine-tuning contextualized representations learned by pre-trained language models remains a prevalent practice in NLP. However, fine-tuning can lead to representation degradation (…
Pyramid-BERT: Reducing Complexity via Successive Core-set based Token Selection
Xin Huang, Ashish Khetan, Rene Bidart +1
Transformer-based language models such as BERT have achieved the state-of-the-art performance on various NLP tasks, but are computationally prohibitive. A recent line of works use…
Amazon SageMaker Model Monitor: A System for Real-Time Insights into Deployed Machine Learning Models
David Nigenda, Zohar Karnin, Muhammad Bilal Zafar +4
With the increasing adoption of machine learning (ML) models and systems in high-stakes settings across different industries, guaranteeing a model's performance after deployment ha…
Improving Early Sepsis Prediction with Multi Modal Learning
Fred Qin, Vivek Madan, Ujjwal Ratan +4
Sepsis is a life-threatening disease with high morbidity, mortality and healthcare costs. The early prediction and administration of antibiotics and intravenous fluids is considere…
Amazon SageMaker Autopilot: a white box AutoML solution at scale
Piali Das, Valerio Perrone, Nikita Ivkin +22
AutoML systems provide a black-box solution to machine learning problems by selecting the right way of processing features, choosing an algorithm and tuning the hyperparameters of…
TabTransformer: Tabular Data Modeling Using Contextual Embeddings
Xin Huang, Ashish Khetan, Milan Cvitkovic +1
We propose TabTransformer, a novel deep tabular data modeling architecture for supervised and semi-supervised learning. The TabTransformer is built upon self-attention based Transf…
GANMEX: One-vs-One Attributions Guided by GAN-based Counterfactual Explanation Baselines
Sheng-Min Shih, Pin-Ju Tien, Zohar Karnin
Attribution methods have been shown as promising approaches for identifying key features that led to learned model predictions. While most existing attribution methods rely on a ba…
Practical and sample efficient zero-shot HPO
Fela Winkelmolen, Nikita Ivkin, H. Furkan Bozkurt +1
Zero-shot hyperparameter optimization (HPO) is a simple yet effective use of transfer learning for constructing a small list of hyperparameter (HP) configurations that complement e…
An Empirical Process Approach to the Union Bound: Practical Algorithms for Combinatorial and Linear Bandits
Julian Katz-Samuels, Lalit Jain, Zohar Karnin +1
This paper proposes near-optimal algorithms for the pure-exploration linear bandit problem in the fixed confidence and fixed budget settings. Leveraging ideas from the theory of su…
PruneNet: Channel Pruning via Global Importance
Ashish Khetan, Zohar Karnin
Channel pruning is one of the predominant approaches for accelerating deep neural networks. Most existing pruning methods either train from scratch with a sparsity inducing term su…
schuBERT: Optimizing Elements of BERT
Ashish Khetan, Zohar Karnin
Transformers \citep{vaswani2017attention} have gradually become a key component for many state-of-the-art natural language representation models. A recent Transformer based model-…
Relative Error Streaming Quantiles
Graham Cormode, Zohar Karnin, Edo Liberty +2
Estimating ranks, quantiles, and distributions over streaming data is a central task in data analysis and monitoring. Given a stream of items from a data universe equipped with…
Streaming Quantiles Algorithms with Small Space and Update Time
Nikita Ivkin, Edo Liberty, Kevin Lang +2
Approximating quantiles and distributions over streaming data has been studied for roughly two decades now. Recently, Karnin, Lang, and Liberty proposed the first asymptotically op…
Asymmetric Random Projections
Nick Ryder, Zohar Karnin, Edo Liberty
Random projections (RP) are a popular tool for reducing dimensionality while preserving local geometry. In many applications the data set to be projected is given to us in advance,…
Discrepancy, Coresets, and Sketches in Machine Learning
Zohar Karnin, Edo Liberty
This paper defines the notion of class discrepancy for families of functions. It shows that low discrepancy classes admit small offline and streaming coresets. We provide general t…
DARC: Differentiable ARchitecture Compression
Shashank Singh, Ashish Khetan, Zohar Karnin
In many learning situations, resources at inference time are significantly more constrained than resources at training time. This paper studies a general paradigm, called Different…
Adaptive Feature Selection: Computationally Efficient Online Sparse Linear Regression under RIP
Satyen Kale, Zohar Karnin, Tengyuan Liang +1
Online sparse linear regression is an online problem where an algorithm repeatedly chooses a subset of coordinates to observe in an adversarially chosen feature vector, makes a rea…
One-Shot Session Recommendation Systems with Combinatorial Items
Yahel David, Dotan Di Castro, Zohar Karnin
In recent years, content recommendation systems in large websites (or \emph{content providers}) capture an increased focus. While the type of content varies, e.g.\ movies, articles…
How Many Folders Do You Really Need?
Mihajlo Grbovic, Guy Halawi, Zohar Karnin +1
Email classification is still a mostly manual task. Consequently, most Web mail users never define a single folder. Recently however, automatic classification offering the same cat…
Optimal Quantile Approximation in Streams
Zohar Karnin, Kevin Lang, Edo Liberty
This paper resolves one of the longest standing basic problems in the streaming computational model. Namely, optimal construction of quantile sketches. An approximate…
Optimal Dynamic Distributed MIS
Keren Censor-Hillel, Elad Haramaty, Zohar Karnin
Finding a maximal independent set (MIS) in a graph is a cornerstone task in distributed computing. The local nature of an MIS allows for fast solutions in a static distributed sett…
Copeland Dueling Bandits
Masrour Zoghi, Zohar Karnin, Shimon Whiteson +1
A version of the dueling bandit problem is addressed in which a Condorcet winner may not exist. Two algorithms are proposed that instead seek to minimize regret with respect to the…
Budget-Constrained Item Cold-Start Handling in Collaborative Filtering Recommenders via Optimal Design
Oren Anava, Shahar Golan, Nadav Golbandi +4
It is well known that collaborative filtering (CF) based recommender systems provide better modeling of users and items associated with considerable rating history. The lack of his…