Search Results for author:
Found 13 papers, 7 papers with code
Equilibrium Aggregation: Encoding Sets via Optimization
Processing sets or other unordered, potentially variable-sized inputs in neural networks is usually handled by aggregating a number of input tensors into a single representation.
Learning a Large Neighborhood Search Algorithm for Mixed Integer Programs
Large Neighborhood Search (LNS) is a combinatorial optimization heuristic that starts with an assignment of values for the variables to be optimized, and iteratively improves it by searching a large neighborhood around the current assignment.
Computer-Aided Design as Language
Computer-Aided Design (CAD) applications are used in manufacturing to model everything from coffee mugs to sports cars.
Solving Mixed Integer Programs Using Neural Networks
Our approach constructs two corresponding neural network-based components, Neural Diving and Neural Branching, to use in a base MIP solver such as SCIP.
Continuous Latent Search for Combinatorial Optimization
Combinatorial optimization problems are notoriously hard because they often require enumeration of the exponentially large solution space.
Meta-Learning Deep Energy-Based Memory Models
We study the problem of learning associative memory -- a system which is able to retrieve a remembered pattern based on its distorted or incomplete version.
Meta-Learning Neural Bloom Filters
There has been a recent trend in training neural networks to replace data structures that have been crafted by hand, with an aim for faster execution, better accuracy, or greater compression.
Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architectures
Here we present results on scaling up biologically motivated models of deep learning on datasets which need deep networks with appropriate architectures to achieve good performance.
Adaptive Cardinality Estimation
The experimental evaluation shows that this approach significantly increases the quality of cardinality estimation, and therefore increases the DBMS performance for some queries by several times or even by several dozens of times.
StarCraft II: A New Challenge for Reinforcement Learning
Finally, we present initial baseline results for canonical deep reinforcement learning agents applied to the StarCraft II domain.
Ranked #1 on
Starcraft II
on MoveToBeacon
Fast Adaptation in Generative Models with Generative Matching Networks
Despite recent advances, the remaining bottlenecks in deep generative models are necessity of extensive training and difficulties with generalization from small number of training examples.
One-shot Learning with Memory-Augmented Neural Networks
Despite recent breakthroughs in the applications of deep neural networks, one setting that presents a persistent challenge is that of "one-shot learning."
Breaking Sticks and Ambiguities with Adaptive Skip-gram
Recently proposed Skip-gram model is a powerful method for learning high-dimensional word representations that capture rich semantic relationships between words.
