
DDPG++: Striving for Simplicity in Continuouscontrol OffPolicy Reinforcement Learning
This paper prescribes a suite of techniques for offpolicy Reinforcement...
read it

Fast, Accurate, and Simple Models for Tabular Data via Augmented Distillation
Automated machine learning (AutoML) can produce complex model ensembles ...
read it

TraDE: Transformers for Density Estimation
We present TraDE, an attentionbased architecture for autoregressive de...
read it

Transformer on a Diet
Transformer has been widely used thanks to its ability to capture sequen...
read it

MetaQLearning
This paper introduces MetaQLearning (MQL), a new offpolicy algorithm ...
read it

P3O: Policyon Policyoff Policy Optimization
Onpolicy reinforcement learning (RL) algorithms have high sample comple...
read it

Language Models with Transformers
The Transformer architecture is superior to RNNbased models in computat...
read it

Compressed Video Action Recognition
Training robust deep video representations has proven to be much more ch...
read it

State Space LSTM Models with Particle MCMC Inference
Long ShortTerm Memory (LSTM) is one of the most powerful sequence model...
read it

Variational Reasoning for Question Answering with Knowledge Graph
Knowledge graph (KG) is known to be helpful for the task of question ans...
read it

A Generic Approach for Escaping Saddle points
A central challenge to using firstorder methods for optimizing nonconve...
read it

Sampling Matters in Deep Embedding Learning
Deep embeddings answer one simple question: How similar are two images? ...
read it

Spectral Methods for Nonparametric Models
Nonparametric models are versatile, albeit computationally expensive, to...
read it

HashBox: Hash Hierarchical Segmentation exploiting Bounding Box Object Detection
We propose a novel approach to address the Simultaneous Detection and Se...
read it

Explaining reviews and ratings with PACO: Poisson Additive CoClustering
Understanding a user's motivations provides valuable information beyond ...
read it

AdaDelay: Delay Adaptive Distributed Stochastic Convex Optimization
We study distributed stochastic convex optimization under the delayed gr...
read it

Graph Partitioning via Parallel Submodular Approximation to Accelerate Distributed Machine Learning
Distributed computing excels at processing large scale data, but the com...
read it

Fast Differentially Private Matrix Factorization
Differentially private collaborative filtering is a challenging task, bo...
read it

ACCAMS: Additive CoClustering to Approximate Matrices Succinctly
Matrix completion and approximation are popular tools to capture a user'...
read it

A la Carte  Learning Fast Kernels
Kernel methods have great promise for learning rich statistical represen...
read it

Robust NearIsometric Matching via Structured Learning of Graphical Models
Models for nearrigid shape matching are typically based on distancerel...
read it
Alexander J. Smola
is this you? claim profile
Director/ Machine Learning at Amazon since 2016, Professor at Carnegie Mellon University Machine Learning Department since 2013, CEO at Marianas Labs 2005, Visiting Scientist at Google Inc., from 20132015, Visiting Scientist at Google, Mountain View 2012, Adjunct Professor at UC Berkeley 2012, Principal Research Scientist at Yahoo! from 20082012, Professor at NICTA from 20042008, Program Leader at National ICT Australia from 20042008, Group Leader at Australian National University from 20012004