40 citations · 137 across the 37 of their papers we have counts for
27 papers · 1 filter
LORENZA: Enhancing Generalization in Low-Rank Gradient LLM Training via Efficient Zeroth-Order Adaptive SAM
Yehonathan Refael, Iftach Arbel, Ofir Lindenbaum +1
We study robust parameter-efficient fine-tuning (PEFT) techniques designed to improve accuracy and generalization while operating within strict computational and memory hardware co…
FineGates: LLMs Finetuning with Compression using Stochastic Gates
Jonathan Svirsky, Yehonathan Refael, Ofir Lindenbaum
Large Language Models (LLMs), with billions of parameters, present significant challenges for full finetuning due to the high computational demands, memory requirements, and imprac…
AdaRankGrad: Adaptive Gradient-Rank and Moments for Memory-Efficient LLMs Training and Fine-Tuning
Yehonathan Refael, Jonathan Svirsky, Boris Shustin +2
Training and fine-tuning large language models (LLMs) come with challenges related to memory and computational requirements due to the increasing size of the model weights and the…
Spectral Self-supervised Feature Selection
Daniel Segal, Ofir Lindenbaum, Ariel Jaffe
Choosing a meaningful subset of features from high-dimensional observations in unsupervised settings can greatly enhance the accuracy of downstream analysis, such as clustering or…
Unveiling Multiple Descents in Unsupervised Autoencoders
Kobi Rahimi, Yehonathan Refael, Tom Tirer +1
The phenomenon of double descent has challenged the traditional bias-variance trade-off in supervised learning but remains unexplored in unsupervised learning, with some studies ar…
Self Supervised Correlation-based Permutations for Multi-View Clustering
Ran Eisenberg, Jonathan Svirsky, Ofir Lindenbaum
Combining data from different sources can improve data analysis tasks such as clustering. However, most of the current multi-view clustering methods are limited to specific domains…
Gappy local conformal auto-encoders for heterogeneous data fusion: in praise of rigidity
Erez Peterfreund, Iryna Burak, Ofir Lindenbaum +4
Fusing measurements from multiple, heterogeneous, partial sources, observing a common object or process, poses challenges due to the increasing availability of numbers and types of…
TabADM: Unsupervised Tabular Anomaly Detection with Diffusion Models
Guy Zamberg, Moshe Salhov, Ofir Lindenbaum +1
Tables are an abundant form of data with use cases across all scientific fields. Real-world datasets often contain anomalous samples that can negatively affect downstream analysis.…
Interpretable Deep Clustering for Tabular Data
Jonathan Svirsky, Ofir Lindenbaum
Clustering is a fundamental learning task widely used as a first step in data analysis. For example, biologists use cluster assignments to analyze genome sequences, medical records…
Anomaly Detection with Variance Stabilized Density Estimation
Amit Rozner, Barak Battash, Henry Li +2
We propose a modified density estimation problem that is highly effective for detecting anomalies in tabular data. Our approach assumes that the density function is relatively stab…
Multi-modal Differentiable Unsupervised Feature Selection
Junchen Yang, Ofir Lindenbaum, Yuval Kluger +1
Multi-modal high throughput biological data presents a great scientific opportunity and a significant computational challenge. In multi-modal measurements, every sample is observed…
Revisiting the Noise Model of Stochastic Gradient Descent
Barak Battash, Ofir Lindenbaum
The stochastic gradient noise (SGN) is a significant factor in the success of stochastic gradient descent (SGD). Following the central limit theorem, SGN was initially modeled as G…
Domain-Generalizable Multiple-Domain Clustering
Amit Rozner, Barak Battash, Lior Wolf +1
This work generalizes the problem of unsupervised domain generalization to the case in which no labeled samples are available (completely unsupervised). We are given unlabeled samp…
Imbalanced Classification via a Tabular Translation GAN
Jonathan Gradstein, Moshe Salhov, Yoav Tulpan +2
When presented with a binary classification problem where the data exhibits severe class imbalance, most standard predictive methods may fail to accurately model the minority class…
Probabilistic Robust Autoencoders for Outlier Detection
Ofir Lindenbaum, Yariv Aizenbud, Yuval Kluger
Anomalies (or outliers) are prevalent in real-world empirical observations and potentially mask important underlying structures. Accurate identification of anomalous samples is cru…
Locally Sparse Neural Networks for Tabular Biomedical Data
Junchen Yang, Ofir Lindenbaum, Yuval Kluger
Tabular datasets with low-sample-size or many variables are prevalent in biomedicine. Practitioners in this domain prefer linear or tree-based models over neural networks since the…
-based Sparse Canonical Correlation Analysis
Ofir Lindenbaum, Moshe Salhov, Amir Averbuch +1
Canonical Correlation Analysis (CCA) models are powerful for studying the associations between two sets of variables. The canonically correlated representations, termed \textit{can…
Differentiable Unsupervised Feature Selection based on a Gated Laplacian
Ofir Lindenbaum, Uri Shaham, Jonathan Svirsky +2
Scientific observations may consist of a large number of variables (features). Identifying a subset of meaningful features is often ignored in unsupervised learning, despite its po…
LOCA: LOcal Conformal Autoencoder for standardized data coordinates
Erez Peterfreund, Ofir Lindenbaum, Felix Dietrich +4
We propose a deep-learning based method for obtaining standardized data coordinates from scientific measurements.Data observations are modeled as samples from an unknown, non-linea…
The Spectral Underpinning of word2vec
Ariel Jaffe, Yuval Kluger, Ofir Lindenbaum +3
word2vec due to Mikolov \textit{et al.} (2013) is a word embedding method that is widely used in natural language processing. Despite its great success and frequent use, theoretica…
Variational Diffusion Autoencoders with Random Walk Sampling
Henry Li, Ofir Lindenbaum, Xiuyuan Cheng +1
Variational autoencoders (VAEs) and generative adversarial networks (GANs) enjoy an intuitive connection to manifold learning: in training the decoder/generator is optimized to app…
Feature Selection using Stochastic Gates
Yutaro Yamada, Ofir Lindenbaum, Sahand Negahban +1
Feature selection problems have been extensively studied for linear estimation, for instance, Lasso, but less emphasis has been placed on feature selection for non-linear functions…
Geometry-Based Data Generation
Ofir Lindenbaum, Jay S. Stanley, Guy Wolf +1
Many generative models attempt to replicate the density of their input data. However, this approach is often undesirable, since data density is highly affected by sampling biases,…
Kernel Scaling for Manifold Learning and Classification
Ofir Lindenbaum, Moshe Salhov, Arie Yeredor +1
Kernel methods play a critical role in many machine learning algorithms. They are useful in manifold learning, classification, clustering and other data analysis tasks. Setting the…