research
∙
08/11/2023
BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents
The massive successes of large language models (LLMs) encourage the emer...
share
research
∙
08/04/2023
Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization
Recent months have seen the emergence of a powerful new trend in which l...
research
∙
07/18/2023
REX: Rapid Exploration and eXploitation for AI Agents
In this paper, we propose an enhanced approach for Rapid Exploration and...
research
∙
03/10/2023
On the Unlikelihood of D-Separation
Causal discovery aims to recover a causal graph from data generated by i...
research
∙
10/21/2021
Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization
In Domain Generalization (DG) settings, models trained on a given set of...
research
∙
10/19/2021
Momentum Contrastive Autoencoder: Using Contrastive Learning for Latent Space Distribution Matching in WAE
Wasserstein autoencoder (WAE) shows that matching two distributions is e...
research
∙
10/19/2021
Learning Rich Nearest Neighbor Representations from Self-supervised Ensembles
Pretraining convolutional neural networks via self-supervision, and appl...
research
∙
09/20/2021
Merlion: A Machine Learning Library for Time Series
We introduce Merlion, an open-source machine learning library for time s...
research
∙
12/28/2020
Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization
The early phase of training has been shown to be important in two ways f...
research
∙
02/21/2020
The Break-Even Point on Optimization Trajectories of Deep Neural Networks
The early phase of training of deep neural networks is critical for thei...
research
∙
02/20/2020
Neural Bayes: A Generic Parameterization Method for Unsupervised Representation Learning
We introduce a parameterization method called Neural Bayes which allows ...
research
∙
10/01/2019
Entropy Penalty: Towards Generalization Beyond the IID Assumption
It has been shown that instead of learning actual object features, deep ...
research
∙
06/05/2019
How to Initialize your Network? Robust Initialization for WeightNorm & ResNets
Residual networks (ResNet) and weight normalization play an important ro...
research
∙
01/11/2019
The Benefits of Over-parameterization at Initialization in Deep ReLU Networks
It has been noted in existing literature that over-parameterization in R...
research
∙
10/06/2018
h-detach: Modifying the LSTM Gradient Towards Better Optimization
Recurrent neural networks are known for their notorious exploding and va...
research
∙
06/22/2018
On the Spectral Bias of Deep Neural Networks
It is well known that over-parametrized deep neural networks (DNNs) are ...
research
∙
02/24/2018
A Walk with SGD
Exploring why stochastic gradient descent (SGD) based optimization metho...
research
∙
11/15/2017
Variational Bi-LSTMs
Recurrent neural networks like long short-term memory (LSTM) are importa...
research
∙
11/13/2017
Three Factors Influencing Minima in SGD
We study the properties of the endpoint of stochastic gradient descent (...
research
∙
10/31/2017
Fraternal Dropout
Recurrent neural networks (RNNs) are important class of architectures am...
research
∙
10/13/2017
Residual Connections Encourage Iterative Inference
Residual networks (Resnets) have become a prominent architecture in deep...
research
∙
06/16/2017
A Closer Look at Memorization in Deep Networks
We examine the role of memorization in deep learning, drawing connection...
research
∙
05/23/2016
On Optimality Conditions for Auto-Encoder Signal Recovery
Auto-Encoders are unsupervised models that aim to learn patterns from ob...
research
∙
03/04/2016
Normalization Propagation: A Parametric Technique for Removing Internal Covariate Shift in Deep Networks
While the authors of Batch Normalization (BN) identify and address an im...
research
∙
05/21/2015
Why Regularized Auto-Encoders learn Sparse Representation?
While the authors of Batch Normalization (BN) identify and address an im...
research
∙
12/07/2014
Dimensionality Reduction with Subspace Structure Preservation
Modeling data as being sampled from a union of independent subspaces has...
research
∙
05/06/2014
Is Joint Training Better for Deep Auto-Encoders?
Traditionally, when generative models of data are developed via deep arc...
research
∙
01/17/2014