
Posthoc Models for Performance Estimation of Machine Learning Inference
Estimating how well a machine learning model performs during inference i...
read it

Certainty Equivalent Quadratic Control for Markov Jump Systems
Realworld control applications often involve complex dynamics subject t...
read it

Generalization Guarantees for Neural Architecture Search with TrainValidation Split
Neural Architecture Search (NAS) is a popular method for automatically d...
read it

Unsupervised Multisource Domain Adaptation Without Access to Source Data
Unsupervised Domain Adaptation (UDA) aims to learn a predictor model for...
read it

LabelImbalanced and GroupSensitive Classification under Overparameterization
Labelimbalanced and groupsensitive classification seeks to appropriate...
read it

SuperConvergence with an Unstable Learning Rate
Conventional wisdom dictates that learning rate should be in the stable ...
read it

Sample Efficient Subspacebased Representations for Nonlinear MetaLearning
Constructing good representations is critical for learning complex tasks...
read it

Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks
Deep networks are typically trained with many more parameters than the s...
read it

On the Marginal Benefit of Active Learning: Does SelfSupervision Eat Its Cake?
Active learning is the set of techniques for intelligently labeling larg...
read it

Theoretical Insights Into Multiclass Classification: A Highdimensional Asymptotic View
Contemporary machine learning applications often involve classification ...
read it

Unsupervised Paraphrasing via Deep Reinforcement Learning
Paraphrasing is expressing the meaning of an input sentence in different...
read it

Statistical and Algorithmic Insights for Semisupervised Learning with Selftraining
Selftraining is a classical approach in semisupervised learning which ...
read it

Exploring Weight Importance and Hessian Bias in Model Pruning
Model pruning is an essential procedure for building compact and computa...
read it

On the Role of Dataset Quality and Heterogeneity in Model Confidence
Safetycritical applications require machine learning models that output...
read it

Nonasymptotic and Accurate Learning of Nonlinear Dynamical Systems
We consider the problem of learning stabilizable systems governed by non...
read it

Quickly Finding the Best Linear Model in High Dimensions
We study the problem of finding the best linear model that can minimize ...
read it

Generalization Guarantees for Neural Networks via Harnessing the Lowrank Structure of the Jacobian
Modern neural network architectures often generalize well despite contai...
read it

Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks
Modern neural networks are typically trained in an overparameterized re...
read it

Towards moderate overparameterization: global convergence guarantees for training shallow neural networks
Many modern neural network architectures are trained in an overparameter...
read it

Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?
Many modern learning tasks involve fitting nonlinear models to data whic...
read it

Stochastic Gradient Descent Learns State Equations with Nonlinear Activations
We study discrete time dynamical systems governed by the state equation ...
read it

Nonasymptotic Identification of LTI Systems from a Single Trajectory
We consider the problem of learning a realization for a linear timeinva...
read it

Endtoend Learning of a Convolutional Neural Network via Deep Tensor Decomposition
In this paper we study the problem of learning the weights of a deep con...
read it

Learning Compact Neural Networks with Regularization
We study the impact of regularization for learning neural networks. Our ...
read it

Learning Feature Nonlinearities with NonConvex Regularized Binned Regression
For various applications, the relations between the dependent and indepe...
read it

Fast and Reliable Parameter Estimation from Nonlinear Observations
In this paper we study the problem of recovering a structured but unknow...
read it

Universality laws for randomized dimension reduction, with applications
Dimension reduction is the process of embedding highdimensional data in...
read it

Isometric sketching of any set via the Restricted Isometry Property
In this paper we show that for the purposes of dimensionality reduction ...
read it

Finding Dense Clusters via "Low Rank + Sparse" Decomposition
Finding "densely connected clusters" in a graph is in general an importa...
read it

New Null Space Results and Recovery Thresholds for Matrix Rank Minimization
Nuclear norm minimization (NNM) has recently gained significant attentio...
read it
Samet Oymak
is this you? claim profile