Search Results for author:
Found 57 papers, 23 papers with code
Sub-linear Memory Sketches for Near Neighbor Search on Streaming Data with RACE
We present the first sublinear memory sketch that can be queried to find the nearest neighbors in a dataset.
Training LLM-based Tutors to Improve Student Learning Outcomes in Dialogues
Specifically, we generate a set of candidate tutor utterances and score them using (1) an LLM-based student model to predict the chance of correct student responses and (2) a pedagogical rubric evaluated by GPT-4o.
Self-Improving Diffusion Models with Synthetic Data
Unfortunately, training new generative models with synthetic data from current or past generation models creates an autophagous (self-consuming) loop that degrades the quality and/or diversity of the synthetic data in what has been termed model autophagy disorder (MAD) and model collapse.
Ranked #1 on
Image Generation
on ImageNet 64x64
On the Geometry of Deep Learning
In this paper, we overview one promising avenue of progress at the mathematical foundation of deep learning: the connection between deep networks and function approximation by affine splines (continuous piecewise linear functions in multiple dimensions).
MalAlgoQA: Pedagogical Evaluation of Counterfactual Reasoning in Large Language Models and Implications for AI in Education
We propose the Malgorithm Identification task, where LLMs are assessed based on their ability to identify corresponding malgorithm given an incorrect answer choice.
Synthetic Context Generation for Question Generation
Despite rapid advancements in large language models (LLMs), QG remains a challenging problem due to its complicated process, open-ended nature, and the diverse settings in which question generation occurs.
ScaLES: Scalable Latent Exploration Score for Pre-Trained Generative Networks
We develop Scalable Latent Exploration Score (ScaLES) to mitigate over-exploration in Latent Space Optimization (LSO), a popular method for solving black-box discrete optimization problems.
Deep Networks Always Grok and Here is Why
Grokking, or delayed generalization, is a phenomenon where generalization in a deep neural network (DNN) occurs long after achieving near zero training error.
Perspectives on the State and Future of Deep Learning -- 2023
The goal of this series is to chronicle opinions and issues in the field of machine learning as they stand today and as they change over time.
Training Dynamics of Deep Network Linear Regions
First, we present a novel statistic that encompasses the local complexity (LC) of the DN based on the concentration of linear regions inside arbitrary dimensional neighborhoods around data points.
MultiQG-TI: Towards Question Generation from Multi-modal Sources
We study the new problem of automatic question generation (QG) from multi-modal sources containing images and texts, significantly expanding the scope of most of the existing work that focuses exclusively on QG from only textual sources.
SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries
In this paper, we go one step further by developing the first provably exact method for computing the geometry of a DN's mapping - including its decision boundary - over a specified region of the data space.
Unsupervised Learning of Sampling Distributions for Particle Filters
Thus, the crux of particle filters lies in designing sampling distributions that are both easy to sample from and lead to accurate estimators.
Retrieval-based Controllable Molecule Generation
On various tasks ranging from simple design criteria to a challenging real-world scenario for designing lead compounds that bind to the SARS-CoV-2 main protease, we demonstrate our approach extrapolates well beyond the retrieval database, and achieves better performance and wider applicability than previous methods.
Automated Scoring for Reading Comprehension via In-context BERT Tuning
Our approach, in-context BERT fine-tuning, produces a single shared scoring model for all items with a carefully-designed input structure to provide contextual information on each item.
Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspective
We also use decision boundary methods to visualize double descent phenomena.
No More Than 6ft Apart: Robust K-Means via Radius Upper Bounds
We propose to remedy such a scenario by introducing a maximal radius constraint $r$ on the clusters formed by the centroids, i. e., samples from the same cluster should not be more than $2r$ apart in terms of $\ell_2$ distance.
Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values
We present Polarity Sampling, a theoretically justified plug-and-play method for controlling the generation quality and diversity of pre-trained deep generative networks DGNs).
Ranked #1 on
Image Generation
on LSUN Car 512 x 384
Spatial Transformer K-Means
This enables (i) the reduction of intrinsic nuisances associated with the data, reducing the complexity of the clustering task and increasing performances and producing state-of-the-art results, (ii) clustering in the input space of the data, leading to a fully interpretable clustering algorithm, and (iii) the benefit of convergence guarantees.
Covariate Balancing Methods for Randomized Controlled Trials Are Not Adversarially Robust
Covariate balancing methods increase the similarity between the distributions of the two groups' covariates.
MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining
Deep Generative Networks (DGNs) are extensively employed in Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and their variants to approximate the data manifold and distribution.
Ranked #4 on
Image Generation
on FFHQ 1024 x 1024
Embedding models through the lens of Stable Coloring
Grounded on this framework, we show that many algorithms ranging across different domains are, in fact, searching for continuous stable coloring solutions of an underlying graph corresponding to the domain.
A Step-Wise Weighting Approach for Controllable Text Generation
Many existing approaches either require extensive training/fine-tuning of the LM for each single attribute under control or are slow to generate text.
Thermal Image Processing via Physics-Inspired Deep Networks
We introduce DeepIR, a new thermal image processing framework that combines physically accurate sensor modeling with deep network-based image representation.
A Case Study in Bootstrapping Ontology Graphs from Textbooks
Ontology graphs are graphs in which the nodes are generic classes and edges have labels that specify the relationships between the classes.
Double Descent and Other Interpolation Phenomena in GANs
We show that overparameterization can improve generalization performance and accelerate the training process.
Math Operation Embeddings for Open-ended Solution Analysis and Feedback
Feedback on student answers and even during intermediate steps in their solutions to open-ended questions is an important element in math education.
Fast Jacobian-Vector Product for Deep Networks
Jacobian-vector products (JVPs) form the backbone of many recent developments in Deep Networks (DNs), with applications including faster constrained optimization, regularization with generalization guarantees, and adversarial example sensitivity assessments.
Max-Affine Spline Insights Into Deep Network Pruning
In this paper, we study the importance of pruning in Deep Networks (DNs) and the yin & yang relationship between (1) pruning highly overparametrized DNs that have been trained from random initialization and (2) training small DNs that have been "cleverly" initialized.
SASSI -- Super-Pixelated Adaptive Spatio-Spectral Imaging
Hence, a scene-adaptive spatial sampling of an hyperspectral scene, guided by its super-pixel segmented image, is capable of obtaining high-quality reconstructions.
Interpretable Image Clustering via Diffeomorphism-Aware K-Means
We design an interpretable clustering algorithm aware of the nonlinear structure of image manifolds.
Enhanced Recurrent Neural Tangent Kernels for Non-Time-Series Data
Kernels derived from deep neural networks (DNNs) in the infinite-width regime provide not only high performance in a range of machine learning tasks but also new theoretical insights into DNN training dynamics and generalization.
Analytical Probability Distributions and Exact Expectation-Maximization for Deep Generative Networks
Deep Generative Networks (DGNs) with probabilistic modeling of their output and latent space are currently trained via Variational Autoencoders (VAEs).
Deep Autoencoders: From Understanding to Generalization Guarantees
Our regularizations leverage recent advances in the group of transformation learning to enable AEs to better approximate the data manifold without explicitly defining the group underlying the manifold.
The Recurrent Neural Tangent Kernel
The study of deep neural networks (DNNs) in the infinite-width limit, via the so-called neural tangent kernel (NTK) approach, has provided new insights into the dynamics of learning, generalization, and the impact of initialization.
VarFA: A Variational Factor Analysis Framework For Efficient Bayesian Learning Analytics
We propose VarFA, a variational inference factor analysis framework that extends existing factor analysis models for educational data mining to efficiently output uncertainty estimation in the model's estimated factors.
Max-Affine Spline Insights into Deep Generative Networks
We also derive the output probability density mapped onto the generated manifold in terms of the latent space density, which enables the computation of key statistics such as its Shannon entropy.
A GOODNESS OF FIT MEASURE FOR GENERATIVE NETWORKS
We define a goodness of fit measure for generative networks which captures how well the network can generate the training data, which is necessary to learn the true data distribution.
Dual Dynamic Inference: Enabling More Efficient, Adaptive and Controllable Deep Inference
State-of-the-art convolutional neural networks (CNNs) yield record-breaking predictive performance, yet at the cost of high-energy-consumption inference, that prohibits their widely deployments in resource-constrained Internet of Things (IoT) applications.
The Geometry of Deep Networks: Power Diagram Subdivision
The subdivision process constrains the affine maps on the (exponentially many) power diagram regions to greatly reduce their complexity.
A MAX-AFFINE SPLINE PERSPECTIVE OF RECURRENT NEURAL NETWORKS
Second, we show that the affine parameter of an RNN corresponds to an input-specific template, from which we can interpret an RNN as performing a simple template matching (matched filtering) given the input.
EnergyNet: Energy-Efficient Dynamic Inference
The prohibitive energy cost of running high-performance Convolutional Neural Networks (CNNs) has been limiting their deployment on resource-constrained platforms including mobile and wearable devices.
Spline Filters For End-to-End Deep Learning
We propose to tackle the problem of end-to-end learning for raw waveform signals by introducing learnable continuous time-frequency atoms.
Mad Max: Affine Spline Insights into Deep Learning
For instance, conditioned on the input signal, the output of a MASO DN can be written as a simple affine transformation of the input.
Semi-Supervised Learning Enabled by Multiscale Deep Neural Network Inversion
Deep Neural Networks (DNNs) provide state-of-the-art solutions in several difficult machine perceptual tasks.
Overcomplete Frame Thresholding for Acoustic Scene Analysis
In this work, we derive a generic overcomplete frame thresholding scheme based on risk minimization.
Deep Neural Networks
Deep Neural Networks (DNNs) are universal function approximators providing state-of- the-art solutions on wide range of applications.
FlatCam: Thin, Bare-Sensor Cameras using Coded Aperture and Computation
FlatCam is a thin form-factor lensless camera that consists of a coded mask placed on top of a bare, conventional sensor array.
FASTA: A Generalized Implementation of Forward-Backward Splitting
This is a user manual for the software package FASTA.
Mathematical Software Numerical Analysis Numerical Analysis
Fast Sublinear Sparse Representation using Shallow Tree Matching Pursuit
Sparse approximations using highly over-complete dictionaries is a state-of-the-art tool for many imaging applications including denoising, super-resolution, compressive sensing, light-field analysis, and object recognition.
A Field Guide to Forward-Backward Splitting with a FASTA Implementation
Non-differentiable and constrained optimization play a key role in machine learning, signal and image processing, communications, and beyond.
Numerical Analysis G.1.6
When in Doubt, SWAP: High-Dimensional Sparse Recovery from Correlated Measurements
We consider the problem of accurately estimating a high-dimensional sparse vector using a small number of linear measurements that are contaminated by noise.
The STONE Transform: Multi-Resolution Image Enhancement and Real-Time Compressive Video
Compressed sensing enables the reconstruction of high-resolution signals from under-sampled data.
Adaptive Primal-Dual Hybrid Gradient Methods for Saddle-Point Problems
The Primal-Dual hybrid gradient (PDHG) method is a powerful optimization scheme that breaks complex problems into simple sub-steps.
Numerical Analysis 65K15 G.1.6
SpaRCS: Recovering low-rank and sparse matrices from compressive measurements
We consider the problem of recovering a matrix $\mathbf{M}$ that is the sum of a low-rank matrix $\mathbf{L}$ and a sparse matrix $\mathbf{S}$ from a small set of linear measurements of the form $\mathbf{y} = \mathcal{A}(\mathbf{M}) = \mathcal{A}({\bf L}+{\bf S})$.
Sparse Signal Recovery Using Markov Random Fields
Compressive Sensing (CS) combines sampling and compression into a single sub-Nyquist linear measurement process for sparse and compressible signals.
Random Projections for Manifold Learning
First, we show that with a small number $M$ of {\em random projections} of sample points in $\reals^N$ belonging to an unknown $K$-dimensional Euclidean manifold, the intrinsic dimension (ID) of the sample set can be estimated to high accuracy.
