output
20132026
most citedDueling Network Architectures for Deep Reinforcement Learning

1.8k citations

Showing 2018Show all

7 papers · 1 filter

cs.PL2018★ 6 cited

Effect Handling for Composable Program Transformations in Edward2

Dave Moore, Maria I. Gorinova

Algebraic effects and handlers have emerged in the programming languages community as a convenient, modular abstraction for controlling computational effects. They have found sever…

cs.LG2018★ 2 cited

Effective Parallelisation for Machine Learning

Michael Kamp, Mario Boley, Olana Missura +1

We present a novel parallelisation scheme that simplifies the adaptation of learning algorithms to growing amounts of data as well as growing needs for accurate and confident predi…

cs.CL2018★ 7 cited

Syntactic Scaffolds for Semantic Structures

Swabha Swayamdipta, Sam Thomson, Kenton Lee +3

We introduce the syntactic scaffold, an approach to incorporating syntactic information into semantic tasks. Syntactic scaffolds avoid expensive syntactic processing at runtime, on…

cs.CL2018★ 13 cited

Prosody Modifications for Question-Answering in Voice-Only Settings

Aleksandr Chuklin, Aliaksei Severyn, Johanne Trippas +3

Many popular form factors of digital assistants---such as Amazon Echo, Apple Homepod, or Google Home---enable the user to hold a conversation with these systems based only on the s…

math.OC2018★ 23 cited

Robust Optimization for Electricity Generation

Chaithanya Bandi, Krishnamurthy Dvijotham, David Morton +1

We consider a robust optimization problem in an electric power system under uncertain demand and availability of renewable energy resources. Solving the deterministic alternating c…

math.OC2018★ 51 cited

Convex Restriction of Power Flow Feasibility Sets

Dongchan Lee, Hung D. Nguyen, Krishnamurthy Dvijotham +1

The convex restriction of the power flow feasible sets identifies the convex subset of power injections where the solution for power flow is guaranteed to exist and satisfy the ope…