Search Results for author: Barnabás Póczos

Found 39 papers, 12 papers with code

VideoOneNet: Bidirectional Convolutional Recurrent OneNet with Trainable Data Steps for Video Processing

1 code implementation ICML 2020 Zoltán Milacski, Barnabás Póczos, Andras Lorincz

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.

Colorization Compressive Sensing +4

The student becomes the master: Matching GPT3 on Scientific Factual Error Correction

no code implementations24 May 2023 Dhananjay Ashok, Atharva Kulkarni, Hai Pham, Barnabás Póczos

Our method is competitive with the very LLM that was used to generate the annotated dataset -- with GPT3. 5 achieving 89. 5% and 60% correction accuracy on SciFact and SciFact-Open, despite using 1250 times as many parameters as our model.

On the Algorithmic Stability and Generalization of Adaptive Optimization Methods

no code implementations8 Nov 2022 Han Nguyen, Hai Pham, Sashank J. Reddi, Barnabás Póczos

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

no code implementations8 Jun 2021 Otilia Stretcu, Emmanouil Antonios Platanios, Tom M. Mitchell, Barnabás Póczos

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

1 code implementation16 Apr 2021 George Stoica, Emmanouil Antonios Platanios, Barnabás Póczos

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.

Relation Extraction

StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfer

2 code implementations NAACL 2021 Yiwei Lyu, Paul Pu Liang, Hai Pham, Eduard Hovy, Barnabás Póczos, Ruslan Salakhutdinov, Louis-Philippe Morency

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.

Benchmarking Style Transfer +1

Improving Relation Extraction by Leveraging Knowledge Graph Link Prediction

1 code implementation9 Dec 2020 George Stoica, Emmanouil Antonios Platanios, Barnabás Póczos

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.

Link Prediction Multi-Task Learning +1

Efficient Meta Lifelong-Learning with Limited Memory

no code implementations EMNLP 2020 ZiRui Wang, Sanket Vaibhav Mehta, Barnabás Póczos, Jaime Carbonell

State-of-the-art lifelong language learning methods store past examples in episodic memory and replay them at both training and inference time.

Multi-Task Learning Question Answering +2

Minimizing FLOPs to Learn Efficient Sparse Representations

1 code implementation ICLR 2020 Biswajit Paria, Chih-Kuan Yeh, Ian E. H. Yen, Ning Xu, Pradeep Ravikumar, Barnabás Póczos

Deep representation learning has become one of the most widely adopted approaches for visual search, recommendation, and identification.

Quantization Representation Learning +1

Contextual Parameter Generation for Knowledge Graph Link Prediction

1 code implementation3 Apr 2020 George Stoica, * Otilia Stretcu, * Emmanouil Antonios Platanios, * Tom M. Mitchell, Barnabás Póczos

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.

Entity Embeddings Link Prediction

LucidDream: Controlled Temporally-Consistent DeepDream on Videos

no code implementations27 Nov 2019 Joel Ruben Antony Moniz, Eunsu Kang, Barnabás Póczos

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

1 code implementation NeurIPS 2019 Simon S. Du, Kangcheng Hou, Barnabás Póczos, Ruslan Salakhutdinov, Ruosong Wang, Keyulu Xu

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.

Graph Classification

LBS Autoencoder: Self-supervised Fitting of Articulated Meshes to Point Clouds

no code implementations CVPR 2019 Chun-Liang Li, Tomas Simon, Jason Saragih, Barnabás Póczos, Yaser Sheikh

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

no code implementations26 Feb 2019 Chun-Liang Li, Wei-Cheng Chang, Youssef Mroueh, Yiming Yang, Barnabás Póczos

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.

Text Generation

Nonparametric Density Estimation & Convergence Rates for GANs under Besov IPM Losses

no code implementations NeurIPS 2019 Ananya Uppal, Shashank Singh, Barnabás Póczos

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.

Density Estimation

Characterizing and Avoiding Negative Transfer

no code implementations CVPR 2019 Zirui Wang, Zihang Dai, Barnabás Póczos, Jaime Carbonell

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.

Transfer Learning

Learning to Predict the Cosmological Structure Formation

1 code implementation15 Nov 2018 Siyu He, Yin Li, Yu Feng, Shirley Ho, Siamak Ravanbakhsh, Wei Chen, Barnabás Póczos

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

no code implementations30 May 2018 Biswajit Paria, Kirthevasan Kandasamy, Barnabás Póczos

We also study a notion of regret in the multi-objective setting and show that our strategy achieves sublinear regret.

Bayesian Optimization

Cautious Deep Learning

no code implementations24 May 2018 Yotam Hechtlinger, Barnabás Póczos, Larry Wasserman

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.

Conformal Prediction

Nonparametric Density Estimation under Adversarial Losses

no code implementations NeurIPS 2018 Shashank Singh, Ananya Uppal, Boyue Li, Chun-Liang Li, Manzil Zaheer, Barnabás Póczos

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.

Density Estimation

Minimax Estimation of Quadratic Fourier Functionals

no code implementations30 Mar 2018 Shashank Singh, Bharath K. Sriperumbudur, Barnabás Póczos

We study estimation of (semi-)inner products between two nonparametric probability distributions, given IID samples from each distribution.


Minimax Distribution Estimation in Wasserstein Distance

no code implementations24 Feb 2018 Shashank Singh, Barnabás Póczos

The Wasserstein metric is an important measure of distance between probability distributions, with applications in machine learning, statistics, probability theory, and data analysis.

BIG-bench Machine Learning

Transformation Autoregressive Networks

no code implementations ICML 2018 Junier B. Oliva, Avinava Dubey, Manzil Zaheer, Barnabás Póczos, Ruslan Salakhutdinov, Eric P. Xing, Jeff Schneider

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.

Density Estimation Outlier Detection

On the Reconstruction Risk of Convolutional Sparse Dictionary Learning

1 code implementation29 Aug 2017 Shashank Singh, Barnabás Póczos, Jian Ma

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.

Dictionary Learning Time Series +1

MMD GAN: Towards Deeper Understanding of Moment Matching Network

2 code implementations NeurIPS 2017 Chun-Liang Li, Wei-Cheng Chang, Yu Cheng, Yiming Yang, Barnabás Póczos

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.

The Multi-fidelity Multi-armed Bandit

no code implementations NeurIPS 2016 Kirthevasan Kandasamy, Gautam Dasarathy, Jeff Schneider, Barnabás Póczos

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

no code implementations NeurIPS 2016 Shashank Singh, Barnabás Póczos

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

1 code implementation NeurIPS 2016 Shashank Singh, Simon S. Du, Barnabás Póczos

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.

Two-sample testing

Analysis of k-Nearest Neighbor Distances with Application to Entropy Estimation

no code implementations28 Mar 2016 Shashank Singh, Barnabás Póczos

Estimating entropy and mutual information consistently is important for many machine learning applications.

Generalized Exponential Concentration Inequality for Rényi Divergence Estimation

no code implementations28 Mar 2016 Shashank Singh, Barnabás Póczos

Estimating divergences in a consistent way is of great importance in many machine learning tasks.

BIG-bench Machine Learning

Deep Mean Maps

no code implementations13 Nov 2015 Junier B. Oliva, Danica J. Sutherland, Barnabás Póczos, Jeff Schneider

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

no code implementations24 Sep 2015 Danica J. Sutherland, Junier B. Oliva, Barnabás Póczos, Jeff Schneider

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.

BIG-bench Machine Learning

Kernels on Sample Sets via Nonparametric Divergence Estimates

no code implementations1 Feb 2012 Danica J. Sutherland, Liang Xiong, Barnabás Póczos, Jeff Schneider

Most machine learning algorithms, such as classification or regression, treat the individual data point as the object of interest.

Anomaly Detection BIG-bench Machine Learning +2

Group Anomaly Detection using Flexible Genre Models

no code implementations NeurIPS 2011 Liang Xiong, Barnabás Póczos, Jeff G. Schneider

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.

Group Anomaly Detection

Estimation of Rényi Entropy and Mutual Information Based on Generalized Nearest-Neighbor Graphs

no code implementations NeurIPS 2010 Dávid Pál, Barnabás Póczos, Csaba Szepesvári

We present simple and computationally efficient nonparametric estimators of R\'enyi entropy and mutual information based on an i. i. d.

Cannot find the paper you are looking for? You can Submit a new open access paper.