Sitemap
A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.
Pages
Posts
Hello world
Published:
My goal for this website is to host a collection of my academic and open-source work for those interested. On some occasions, I may post about software engineering challenges I have encountered.
portfolio
Bayesian optimization package
Sample a Gaussian process that is actively learned.
publications
A comparison of neural network training methods for text classification
Published in arXiv, 2013
Benchmark of stochastic gradient descent and Nesterov’s accelerated gradient for text classification.
Recommended citation: Anderson de Andrade. (2013). "A comparison of neural network training methods for text classification." arXiv:1910.12674.
Download Paper
Best practices for convolutional neural networks applied to object recognition in images
Published in arXiv, 2014
Evaluate the performance impact of optimization algorithms, activation functions, dropout, and maxout networks, in CNNs.
Recommended citation: Anderson de Andrade. (2014). "Best practices for convolutional neural networks applied to object recognition in images." arXiv:1910.13029.
Download Paper | Download Slides
Unsupervised aspect extraction from free-form conversations
Published in SIGKDD Workshop on Issues of Sentiment Discovery and Opinion Mining, 2017
Dictionary-based approach for the extraction of “aspect-of” relationships.
Recommended citation: En-Shiun Annie Lee, Richie Wenjie Zi, Afsaneh Fazly, Brandon Seibel, & Anderson de Andrade. (2017). "Unsupervised aspect extraction from free-form conversations." SIGKDD Workshop on Issues of Sentiment Discovery and Opinion Mining.
Download Paper | Download Bibtex
DENS: A dataset for multi-class emotion analysis
Published in EMNLP, 2019
Dataset for emotion classification of long-form narratives.
Recommended citation: Chen Liu, Osama Muhammad, & Anderson de Andrade. (2019). "DENS: A dataset for multi-class emotion analysis." EMNLP.
Download Paper | Download Bibtex
Exploring multilingual syntactic sentence representations
Published in EMNLP Workshop on Noisy User-Generated Text, 2019
Sentence embeddings augmented by universal parts-of-speech tags evaluated on low-resource languages.
Recommended citation: Chen Liu, Anderson de Andrade, & Muhammad Osama. (2019). "Exploring multilingual syntactic sentence representations." EMNLP Workshop on Noisy User-Generated Text.
Download Paper | Download Bibtex
Graph representation learning network via adaptive sampling
Published in arXiv, 2020
Graph representations using a learnable attention mechanism to sample the neighbourhood of a graph.
Recommended citation: Anderson de Andrade, & Chen Liu. (2020). "Graph representation learning network via adaptive sampling." arXiv:2006.04637.
Download Paper | Download Bibtex
An architecture for accelerated large-scale inference of transformer-based language models
Published in NAACL Conference on Human Language Technologies: Industry Papers, 2021
Unified batch and online transformer inference.
Recommended citation: Amir Ganiev, Colt Chapin, Anderson de Andrade, & Chen Liu. (2021). "An architecture for accelerated large-scale inference of transformer-based language models." NAACL Conference on Human Language Technologies: Industry Papers.
Download Paper | Download Bibtex
Conditional and residual methods in scalable coding for humans and machines
Published in ICME Workshop on Coding for Machines, 2023
A comparison between conditional and residual entropy codecs for a two-channel systems of tasks with nested information.
Recommended citation: Anderson de Andrade, Alon Harell, & Ivan Bajić. (2023). "Conditional and residual methods in scalable coding for humans and machines." ICME Workshop on Coding for Machines.
Download Paper | Download Slides | Download Bibtex
Base layer efficiency in scalable human-machine coding
Published in ICIP, 2023
Improving the shared channel in coding for machines (CfM).
Recommended citation: Yalda Foroutan, Alon Harell, Anderson de Andrade, & Ivan Bajić. (2023). "Base layer efficiency in scalable human-machine coding." ICIP.
Download Paper | Download Bibtex
Towards task-compatible compressible representations
Published in ICME Workshop on Coding for Machines, 2024
Task reconstruction loss acts as a regularizer, increasing rate-distortion performance in coding for humans and machines.
Recommended citation: Anderson de Andrade, & Ivan Bajić. (2024). "Towards task-compatible compressible representations." ICME Workshop on Coding for Machines.
Download Paper | Download Slides | Download Bibtex
Rate-distortion theory in coding for machines and its applications
Published in IEEE TPAMI, 2025
Theoretical considerations and evaluation of split and distillation points.
Recommended citation: Alon Harell, Yalda Foroutan, Nilesh A. Ahuja, Parual Datta, Bhavya Kanzariya, V. Srinivasa Somayazulu, Omesh Tickoo, Anderson de Andrade, & Ivan V. Bajic. (2025). "Rate-distortion theory in coding for machines and its applications." IEEE TPAMI.
Download Paper | Download Bibtex
Lossy common information in a learnable Gray-Wyner Network
Published in ICLR, 2026
Isolate the common information between two dependent computer vision tasks.
Recommended citation: Anderson de Andrade, Alon Harell, & Ivan Bajić. (2026). "Lossy common information in a learnable Gray-Wyner Network." ICLR.
Download Paper | Download Slides
Rate-distortion optimization for transformer inference
Published in arXiv, 2026
Split computing for language models, extending the theory of usable information.
Recommended citation: Anderson de Andrade, Alon Harell, & Ivan Bajić. (2026). "Rate-distortion optimization for transformer inference." arXiv:2601.22002.
Download Paper | Download Bibtex
talks
Towards task-compatible compressible representations
Published:
See the slides and more details about the publication here.
A machine learning research toolkit
Published:
A six hour tutorial describing a toolkit for machine learning research. We go over many of the details of our suggested tools for development, deployment, and artifact management. We make emphasis on best practices and our philosophy.
teaching
Teaching assistant: Introduction to engineering analysis (ENSC 180)
Undergraduate course, Simon Fraser University, School of Engineering Science, 2025
Ran lab sessions, graded exams and assignments, held office hours, and assisted students with MATLAB programming and engineering concepts.