Search Results for author:
Found 78 papers, 41 papers with code
Pre-training Small Base LMs with Fewer Tokens
Here we show that smaller LMs trained utilizing some of the layers of GPT2-medium (355M) and GPT-2-large (770M) can effectively match the val loss of their bigger counterparts when trained from scratch for the same number of training steps on OpenWebText dataset with 9B tokens.
Compressed Sensing using Generative Models
The goal of compressed sensing is to estimate a vector from an underdetermined system of noisy linear measurements, by making use of prior knowledge on the structure of vectors in the relevant domain.
Robust Compressed Sensing MRI with Deep Generative Priors
The CSGM framework (Bora-Jalal-Price-Dimakis'17) has shown that deep generative priors can be powerful tools for solving inverse problems.
CausalGAN: Learning Causal Implicit Generative Models with Adversarial Training
We show that adversarial training can be used to learn a generative model with true observational and interventional distributions if the generator architecture is consistent with the given causal graph.
Your Local GAN: Designing Two Dimensional Local Attention Mechanisms for Generative Models
We introduce a new local sparse attention layer that preserves two-dimensional geometry and locality.
Ranked #19 on
Conditional Image Generation
on ImageNet 128x128
Intermediate Layer Optimization for Inverse Problems using Deep Generative Models
We propose Intermediate Layer Optimization (ILO), a novel optimization algorithm for solving inverse problems with deep generative models.
Score-Guided Intermediate Layer Optimization: Fast Langevin Mixing for Inverse Problems
In practice, to allow for increased expressivity, we propose to do posterior sampling in the latent space of a pre-trained generative model.
Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Models
We present the first framework to solve linear inverse problems leveraging pre-trained latent diffusion models.
Multiresolution Textual Inversion
We extend Textual Inversion to learn pseudo-words that represent a concept at different resolutions.
Language models scale reliably with over-training and on downstream tasks
We fit scaling laws that extrapolate in both the number of model parameters and the ratio of training tokens to parameters.
Compressed Sensing with Deep Image Prior and Learned Regularization
We propose a novel method for compressed sensing recovery using untrained deep generative models.
SMYRF: Efficient Attention using Asymmetric Clustering
We also show that SMYRF can be used interchangeably with dense attention before and after training.
SMYRF - Efficient Attention using Asymmetric Clustering
We propose a novel type of balanced clustering algorithm to approximate attention.
Ambient Diffusion: Learning Clean Distributions from Corrupted Data
We present the first diffusion-based framework that can learn an unknown distribution using only highly-corrupted samples.
Model-Powered Conditional Independence Test
We consider the problem of non-parametric Conditional Independence testing (CI testing) for continuous random variables.
Provable Certificates for Adversarial Examples: Fitting a Ball in the Union of Polytopes
We relate the problem of computing pointwise robustness of these networks to that of computing the maximum norm ball with a fixed center that can be contained in a non-convex polytope.
Inverse Problems Leveraging Pre-trained Contrastive Representations
The problem is to recover the representation of an image R(x), if we are only given a corrupted version A(x), for some known forward operator A.
Streaming Weak Submodularity: Interpreting Neural Networks on the Fly
In many machine learning applications, it is important to explain the predictions of a black-box classifier.
Learning a Compressed Sensing Measurement Matrix via Gradient Unrolling
Our experiments show that there is indeed additional structure beyond sparsity in the real datasets; our method is able to discover it and exploit it to create excellent reconstructions with fewer measurements (by a factor of 1. 1-3x) compared to the previous state-of-the-art methods.
The Robust Manifold Defense: Adversarial Training using Generative Models
Our formulation involves solving a min-max problem, where the min player sets the parameters of the classifier and the max player is running our attack, and is thus searching for adversarial examples in the {\em low-dimensional} input space of the spanner.
Discrete Adversarial Attacks and Submodular Optimization with Applications to Text Classification
In this paper we formulate the attacks with discrete input on a set function as an optimization task.
Instance-Optimal Compressed Sensing via Posterior Sampling
We characterize the measurement complexity of compressed sensing of signals drawn from a known prior distribution, even when the support of the prior is the entire space (rather than, say, sparse vectors).
Fairness for Image Generation with Uncertain Sensitive Attributes
This motivates the introduction of definitions that allow algorithms to be \emph{oblivious} to the relevant groupings.
Exactly Computing the Local Lipschitz Constant of ReLU Networks
The local Lipschitz constant of a neural network is a useful metric with applications in robustness, generalization, and fairness evaluation.
Provable Lipschitz Certification for Generative Models
We present a scalable technique for upper bounding the Lipschitz constant of generative models.
Gradient Coding
We propose a novel coding theoretic framework for mitigating stragglers in distributed learning.
Multitasking Models are Robust to Structural Failure: A Neural Model for Bilingual Cognitive Reserve
We find a surprising connection between multitask learning and robustness to neuron failures.
Entropic Causal Inference
We show that the problem of finding the exogenous variable with minimum entropy is equivalent to the problem of finding minimum joint entropy given $n$ marginal distributions, also known as minimum entropy coupling problem.
Single Pass PCA of Matrix Products
In this paper we present a new algorithm for computing a low rank approximation of the product $A^TB$ by taking only a single pass of the two matrices $A$ and $B$.
Robust Compressed Sensing using Generative Models
In analogy to classical compressed sensing, here we assume a generative model as a prior, that is, we assume the vector is represented by a deep generative model $G: \mathbb{R}^k \rightarrow \mathbb{R}^n$.
Optimizing Sampling Patterns for Compressed Sensing MRI with Diffusion Generative Models
Diffusion-based generative models have been used as powerful priors for magnetic resonance imaging (MRI) reconstruction.
Inverting Deep Generative models, One layer at a time
For generative models of arbitrary depth, we show that exact recovery is possible in polynomial time with high probability, if the layers are expanding and the weights are randomly selected.
Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models trained on Corrupted Data
We open-source our code and the trained Ambient Diffusion MRI models: https://github. com/utcsilab/ambient-diffusion-mri .
Sparse Logistic Regression Learns All Discrete Pairwise Graphical Models
We show that this algorithm can recover any arbitrary discrete pairwise graphical model, and also characterize its sample complexity as a function of model width, alphabet size, edge parameter accuracy, and the number of variables.
One-Dimensional Deep Image Prior for Curve Fitting of S-Parameters from Electromagnetic Solvers
DIP is a technique that optimizes the weights of a randomly-initialized convolutional neural network to fit a signal from noisy or under-determined measurements.
Learning Causal Graphs with Small Interventions
We prove that any deterministic adaptive algorithm needs to be a separating system in order to learn complete graphs in the worst case.
Primal-Dual Block Frank-Wolfe
We propose a variant of the Frank-Wolfe algorithm for solving a class of sparse/low-rank optimization problems.
Primal-Dual Block Generalized Frank-Wolfe
We propose a generalized variant of Frank-Wolfe algorithm for solving a class of sparse/low-rank optimization problems.
Which questions should I answer? Salience Prediction of Inquisitive Questions
QSALIENCE is instruction-tuned over our dataset of linguist-annotated salience scores of 1, 766 (context, question) pairs.
Restricted Strong Convexity Implies Weak Submodularity
Our results extend the work of Das and Kempe (2011) from the setting of linear regression to arbitrary objective functions.
Gradient Coding from Cyclic MDS Codes and Expander Graphs
Gradient coding is a technique for straggler mitigation in distributed learning.
Identifying Best Interventions through Online Importance Sampling
Motivated by applications in computational advertising and systems biology, we consider the problem of identifying the best out of several possible soft interventions at a source node $V$ in an acyclic causal directed graph, to maximize the expected value of a target node $Y$ (located downstream of $V$).
Scalable Greedy Feature Selection via Weak Submodularity
Furthermore, we show that a bounded submodularity ratio can be used to provide data dependent bounds that can sometimes be tighter also for submodular functions.
On Approximation Guarantees for Greedy Low Rank Optimization
We provide new approximation guarantees for greedy low rank matrix estimation under standard assumptions of restricted strong convexity and smoothness.
Leveraging Sparsity for Efficient Submodular Data Summarization
The facility location problem is widely used for summarizing large datasets and has additional applications in sensor placement, image retrieval, and clustering.
Exact MAP Inference by Avoiding Fractional Vertices
We require that the number of fractional vertices in the LP relaxation exceeding the optimal solution is bounded by a polynomial in the problem size.
Sparse Quadratic Logistic Regression in Sub-quadratic Time
We consider support recovery in the quadratic logistic regression setting - where the target depends on both p linear terms $x_i$ and up to $p^2$ quadratic terms $x_i x_j$.
Cost-Optimal Learning of Causal Graphs
We consider the problem of learning a causal graph over a set of variables with interventions.
Entropic Causality and Greedy Minimum Entropy Coupling
This framework requires the solution of a minimum entropy coupling problem: Given marginal distributions of m discrete random variables, each on n states, find the joint distribution with minimum entropy, that respects the given marginals.
Contextual Bandits with Latent Confounders: An NMF Approach
Our algorithm achieves a regret of $\mathcal{O}\left(L\mathrm{poly}(m, \log K) \log T \right)$ at time $T$, as compared to $\mathcal{O}(LK\log T)$ for conventional contextual bandits, assuming a constant gap between the best arm and the rest for each context.
Bipartite Correlation Clustering -- Maximizing Agreements
We present a novel approximation algorithm for $k$-BCC, a variant of BCC with an upper bound $k$ on the number of clusters.
Sparse PCA via Bipartite Matchings
We consider the following multi-component sparse PCA problem: given a set of data points, we seek to extract a small number of sparse components with disjoint supports that jointly capture the maximum possible variance.
Stay on path: PCA along graph paths
We introduce a variant of (sparse) PCA in which the set of feasible support sets is determined by a graph.
On the Information Theoretic Limits of Learning Ising Models
We provide a general framework for computing lower-bounds on the sample complexity of recovering the underlying graphs of Ising models, given i. i. d samples.
Sparse Polynomial Learning and Graph Sketching
We give an algorithm for exactly reconstructing f given random examples from the uniform distribution on $\{-1, 1\}^n$ that runs in time polynomial in $n$ and $2s$ and succeeds if the function satisfies the unique sign property: there is one output value which corresponds to a unique set of values of the participating parities.
Sparse PCA through Low-rank Approximations
A key algorithmic component of our scheme is a combinatorial feature elimination step that is provably safe and in practice significantly reduces the running complexity of our algorithm.
Applications of Common Entropy for Causal Inference
We study the problem of discovering the simplest latent variable that can make two observed discrete variables conditionally independent.
Experimental Design for Cost-Aware Learning of Causal Graphs
We consider the minimum cost intervention design problem: Given the essential graph of a causal graph and a cost to intervene on a variable, identify the set of interventions with minimum total cost that can learn any causal graph with the given essential graph.
Adversarial Video Compression Guided by Soft Edge Detection
We propose a video compression framework using conditional Generative Adversarial Networks (GANs).
Orthogonal NMF through Subspace Exploration
Our algorithm relies on a novel approximation to the related Nonnegative Principal Component Analysis (NNPCA) problem; given an arbitrary data matrix, NNPCA seeks $k$ nonnegative components that jointly capture most of the variance.
Gradient Coding: Avoiding Stragglers in Distributed Learning
We propose a novel coding theoretic framework for mitigating stragglers in distributed learning.
AmbientGAN: Generative models from lossy measurements
Generative models provide a way to model structure in complex distributions and have been shown to be useful for many tasks of practical interest.
Quantifying Perceptual Distortion of Adversarial Examples
To demonstrate the value of quantifying the perceptual distortion of adversarial examples, we present and employ a unifying framework fusing different attack styles.
One-dimensional Deep Image Prior for Time Series Inverse Problems
We extend the Deep Image Prior (DIP) framework to one-dimensional signals.
Learning Distributions Generated by One-Layer ReLU Networks
We give a simple algorithm to estimate the parameters (i. e., the weight matrix and bias vector of the ReLU neural network) up to an error $\epsilon||W||_F$ using $\tilde{O}(1/\epsilon^2)$ samples and $\tilde{O}(d^2/\epsilon^2)$ time (log factors are ignored for simplicity).
SGD Learns One-Layer Networks in WGANs
Generative adversarial networks (GANs) are a widely used framework for learning generative models.
Communication-Efficient Asynchronous Stochastic Frank-Wolfe over Nuclear-norm Balls
Large-scale machine learning training suffers from two prior challenges, specifically for nuclear-norm constrained problems with distributed systems: the synchronization slowdown due to the straggling workers, and high communication costs.
Composing Normalizing Flows for Inverse Problems
We approach this problem as a task of conditional inference on the pre-trained unconditional flow model.
Solving Inverse Problems with a Flow-based Noise Model
We study image inverse problems with a normalizing flow prior.
Deep Learning Techniques for Inverse Problems in Imaging
Recent work in machine learning shows that deep neural networks can be used to solve a wide variety of inverse problems arising in computational imaging.
Model-Based Deep Learning
We are interested in hybrid techniques that combine principled mathematical models with data-driven systems to benefit from the advantages of both approaches.
Neural Distributed Source Coding
Distributed source coding (DSC) is the task of encoding an input in the absence of correlated side information that is only available to the decoder.
Deblurring via Stochastic Refinement
Unlike existing techniques, we train a stochastic sampler that refines the output of a deterministic predictor and is capable of producing a diverse set of plausible reconstructions for a given input.
Solving Inverse Problems with NerfGANs
We introduce a novel framework for solving inverse problems using NeRF-style generative models.
Discovering the Hidden Vocabulary of DALLE-2
We discover that DALLE-2 seems to have a hidden vocabulary that can be used to generate images with absurd prompts.
Soft Diffusion: Score Matching for General Corruptions
To reverse these general diffusions, we propose a new objective called Soft Score Matching that provably learns the score function for any linear corruption process and yields state of the art results for CelebA.
Ranked #7 on
Image Generation
on CelebA 64x64
Zonotope Domains for Lagrangian Neural Network Verification
Neural network verification aims to provide provable bounds for the output of a neural network for a given input range.
Restoration-Degradation Beyond Linear Diffusions: A Non-Asymptotic Analysis For DDIM-Type Samplers
We develop a framework for non-asymptotic analysis of deterministic samplers used for diffusion generative modeling.
