
Sparse Communication via Mixed Distributions
Neural networks and other machine learning models compute continuous rep...
read it

Sparse Continuous Distributions and FenchelYoung Losses
Exponential families are widely used in machine learning; they include m...
read it

Learning Binary Trees via Sparse Relaxation
One of the most classical problems in machine learning is how to learn b...
read it

Understanding the Mechanics of SPIGOT: Surrogate Gradients for Latent Structure Learning
Latent structure models are a powerful tool for modeling language data: ...
read it

Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity
Training neural network models with discrete (categorical or structured)...
read it

Sparse and Continuous Attention Mechanisms
Exponential families are widely used in machine learning; they include m...
read it

Sparse and Structured Visual Attention
Visual attention mechanisms are widely used in multimodal tasks, such as...
read it

LPSparseMAP: Differentiable Relaxed Optimization for Sparse Structured Prediction
Structured prediction requires manipulating a large number of combinator...
read it

Adaptively Sparse Transformers
Attention mechanisms have become ubiquitous in NLP. Recent architectures...
read it

Notes on Latent Structure Models and SPIGOT
These notes aim to shed light on the recently proposed structured projec...
read it

Sparse SequencetoSequence Models
Sequencetosequence models are a powerful workhorse of NLP. Most varian...
read it

Learning with FenchelYoung Losses
Over the past decades, numerous loss functions have been been proposed f...
read it

Towards Dynamic Computation Graphs via Sparse Latent Structure
Deep NLP models benefit from underlying structures in the datae.g., p...
read it

Learning Classifiers with FenchelYoung Losses: Generalized Entropies, Margins, and Algorithms
We study in this paper FenchelYoung losses, a generic way to construct ...
read it

SparseMAP: Differentiable Sparse Structured Inference
Structured prediction requires searching over a combinatorial number of ...
read it

A Regularized Framework for Sparse and Structured Neural Attention
Modern neural networks are often augmented with an attention mechanism, ...
read it

Multioutput Polynomial Networks and Factorization Machines
Factorization machines and polynomial networks are supervised polynomial...
read it

Argument Mining with Structured SVMs and RNNs
We propose a novel factor graph model for argument mining, designed for ...
read it

Conversational Markers of Constructive Discussions
Group discussions are essential for organizing every aspect of modern li...
read it

Winning Arguments: Interaction Dynamics and Persuasion Strategies in Goodfaith Online Discussions
Changing someone's opinion is arguably one of the most important challen...
read it

Linguistic Harbingers of Betrayal: A Case Study on an Online Strategy Game
Interpersonal relations are fickle, with close friendships often dissolv...
read it

QUOTUS: The Structure of Political Media Coverage as Revealed by Quoting Patterns
Given the extremely large pool of events and stories available, media ou...
read it
Vlad Niculae
is this you? claim profile