Search Results for author:
Found 44 papers, 14 papers with code
VideoOneNet: Bidirectional Convolutional Recurrent OneNet with Trainable Data Steps for Video Processing
Deep Neural Networks (DNNs) achieve the state-of-the-art results on a wide range of image processing tasks, however, the majority of such solutions are problem-specific, like most AI algorithms.
Chemistry-Inspired Diffusion with Non-Differentiable Guidance
Recent advances in diffusion models have shown remarkable potential in the conditional generation of novel molecules.
Reconstructing Galaxy Cluster Mass Maps using Score-based Generative Modeling
We present a novel approach to reconstruct gas and dark matter projected density maps of galaxy clusters using score-based generative modeling.
Recovering Time-Varying Networks From Single-Cell Data
Gene regulation is a dynamic process that underlies all aspects of human development, disease response, and other key biological processes.
GraphBPE: Molecular Graphs Meet Byte-Pair Encoding
However, less is studied on the data preprocessing schedule for molecular graphs, where a different view of the molecular graph could potentially boost the model's performance.
Greener GRASS: Enhancing GNNs with Encoding, Rewiring, and Attention
It rewires the input graph by superimposing a random regular graph to enhance long-range information propagation.
SciFix: Outperforming GPT3 on Scientific Factual Error Correction
Our method outperforms the very LLM that was used to generate the annotated dataset -- with Few-Shot Prompting on GPT3. 5 achieving 58%, 61%, and 64% on the respective datasets, a consistently lower correction accuracy, despite using nearly 800 times as many parameters as our model.
On the Algorithmic Stability and Generalization of Adaptive Optimization Methods
Despite their popularity in deep learning and machine learning in general, the theoretical properties of adaptive optimizers such as Adagrad, RMSProp, Adam or AdamW are not yet fully understood.
Coarse-to-Fine Curriculum Learning
However, in machine learning, models are most often trained to solve the target tasks directly. Inspired by human learning, we propose a novel curriculum learning approach which decomposes challenging tasks into sequences of easier intermediate goals that are used to pre-train a model before tackling the target task.
Re-TACRED: Addressing Shortcomings of the TACRED Dataset
Finally, aside from our analysis we also release Re-TACRED, a new completely re-annotated version of the TACRED dataset that can be used to perform reliable evaluation of relation extraction models.
StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfer
Many of the existing style transfer benchmarks primarily focus on individual high-level semantic changes (e. g. positive to negative), which enable controllability at a high level but do not offer fine-grained control involving sentence structure, emphasis, and content of the sentence.
Improving Relation Extraction by Leveraging Knowledge Graph Link Prediction
Relation extraction (RE) aims to predict a relation between a subject and an object in a sentence, while knowledge graph link prediction (KGLP) aims to predict a set of objects, O, given a subject and a relation from a knowledge graph.
Efficient Meta Lifelong-Learning with Limited Memory
State-of-the-art lifelong language learning methods store past examples in episodic memory and replay them at both training and inference time.
Minimizing FLOPs to Learn Efficient Sparse Representations
Deep representation learning has become one of the most widely adopted approaches for visual search, recommendation, and identification.
Contextual Parameter Generation for Knowledge Graph Link Prediction
More specifically, we treat relations as the context in which source entities are processed to produce predictions, by using relation embeddings to generate the parameters of a model operating over source entity embeddings.
Ranked #2 on
Link Prediction
on NELL-995
LucidDream: Controlled Temporally-Consistent DeepDream on Videos
In this work, we aim to propose a set of techniques to improve the controllability and aesthetic appeal when DeepDream, which uses a pre-trained neural network to modify images by hallucinating objects into them, is applied to videos.
Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels
While graph kernels (GKs) are easy to train and enjoy provable theoretical guarantees, their practical performances are limited by their expressive power, as the kernel function often depends on hand-crafted combinatorial features of graphs.
LBS Autoencoder: Self-supervised Fitting of Articulated Meshes to Point Clouds
As input, we take a sequence of point clouds to be registered as well as an artist-rigged mesh, i. e. a template mesh equipped with a linear-blend skinning (LBS) deformation space parameterized by a skeleton hierarchy.
Implicit Kernel Learning
While learning the kernel in a data driven way has been investigated, in this paper we explore learning the spectral distribution of kernel via implicit generative models parametrized by deep neural networks.
Nonparametric Density Estimation & Convergence Rates for GANs under Besov IPM Losses
Thus, we show how our results imply bounds on the statistical error of a GAN, showing, for example, that GANs can strictly outperform the best linear estimator.
Kernel Change-point Detection with Auxiliary Deep Generative Models
Detecting the emergence of abrupt property changes in time series is a challenging problem.
Characterizing and Avoiding Negative Transfer
When labeled data is scarce for a specific target task, transfer learning often offers an effective solution by utilizing data from a related source task.
Learning to Predict the Cosmological Structure Formation
We build a deep neural network, the Deep Density Displacement Model (hereafter D$^3$M), to predict the non-linear structure formation of the Universe from simple linear perturbation theory.
A Flexible Framework for Multi-Objective Bayesian Optimization using Random Scalarizations
We also study a notion of regret in the multi-objective setting and show that our strategy achieves sublinear regret.
Cautious Deep Learning
Our construction is based on $p(x|y)$ rather than $p(y|x)$ which results in a classifier that is very cautious: it outputs the null set --- meaning "I don't know" --- when the object does not resemble the training examples.
Nonparametric Density Estimation under Adversarial Losses
We study minimax convergence rates of nonparametric density estimation under a large class of loss functions called "adversarial losses", which, besides classical $\mathcal{L}^p$ losses, includes maximum mean discrepancy (MMD), Wasserstein distance, and total variation distance.
Minimax Estimation of Quadratic Fourier Functionals
We study estimation of (semi-)inner products between two nonparametric probability distributions, given IID samples from each distribution.
Minimax Distribution Estimation in Wasserstein Distance
The Wasserstein metric is an important measure of distance between probability distributions, with applications in machine learning, statistics, probability theory, and data analysis.
Transformation Autoregressive Networks
Further, through a comprehensive study over both real world and synthetic data, we show for that jointly leveraging transformations of variables and autoregressive conditional models, results in a considerable improvement in performance.
Ranked #1 on
Density Estimation
on BSDS300
On the Reconstruction Risk of Convolutional Sparse Dictionary Learning
Sparse dictionary learning (SDL) has become a popular method for adaptively identifying parsimonious representations of a dataset, a fundamental problem in machine learning and signal processing.
MMD GAN: Towards Deeper Understanding of Moment Matching Network
In this paper, we propose to improve both the model expressiveness of GMMN and its computational efficiency by introducing adversarial kernel learning techniques, as the replacement of a fixed Gaussian kernel in the original GMMN.
Query Efficient Posterior Estimation in Scientific Experiments via Bayesian Active Learning
In this paper, we study active posterior estimation in a Bayesian setting when the likelihood is expensive to evaluate.
The Multi-fidelity Multi-armed Bandit
We study a variant of the classical stochastic $K$-armed bandit where observing the outcome of each arm is expensive, but cheap approximations to this outcome are available.
Finite-Sample Analysis of Fixed-k Nearest Neighbor Density Functional Estimators
We provide finite-sample analysis of a general framework for using k-nearest neighbor statistics to estimate functionals of a nonparametric continuous probability density, including entropies and divergences.
Efficient Nonparametric Smoothness Estimation
Sobolev quantities (norms, inner products, and distances) of probability density functions are important in the theory of nonparametric statistics, but have rarely been used in practice, partly due to a lack of practical estimators.
Analysis of k-Nearest Neighbor Distances with Application to Entropy Estimation
Estimating entropy and mutual information consistently is important for many machine learning applications.
Generalized Exponential Concentration Inequality for Rényi Divergence Estimation
Estimating divergences in a consistent way is of great importance in many machine learning tasks.
Deep Mean Maps
The use of distributions and high-level features from deep architecture has become commonplace in modern computer vision.
Linear-time Learning on Distributions with Approximate Kernel Embeddings
This work develops the first random features for pdfs whose dot product approximates kernels using these non-Euclidean metrics, allowing estimators using such kernels to scale to large datasets by working in a primal space, without computing large Gram matrices.
On Variance Reduction in Stochastic Gradient Descent and its Asynchronous Variants
We demonstrate the empirical performance of our method through a concrete realization of asynchronous SVRG.
On the Decreasing Power of Kernel and Distance based Nonparametric Hypothesis Tests in High Dimensions
This paper is about two related decision theoretic problems, nonparametric two-sample testing and independence testing.
Kernels on Sample Sets via Nonparametric Divergence Estimates
Most machine learning algorithms, such as classification or regression, treat the individual data point as the object of interest.
Group Anomaly Detection using Flexible Genre Models
We evaluate the effectiveness of FGM on both synthetic and real data sets including images and turbulence data, and show that it is superior to existing approaches in detecting group anomalies.
Estimation of Rényi Entropy and Mutual Information Based on Generalized Nearest-Neighbor Graphs
We present simple and computationally efficient nonparametric estimators of R\'enyi entropy and mutual information based on an i. i. d.
