Rate-distortion optimization for transformer inference
Anderson de Andrade, Alon Harell, & Ivan Bajić. (2026). "Rate-distortion optimization for transformer inference." arXiv:2601.22002.
Curriculum Vitae
Download my CV as a PDF.
Education
- Ph.D. in Engineering Science, Simon Fraser University, 2027 (expected)
- M.S. in Applied Computing, University of Toronto, 2015
- B.E. in Networks and Communications, Universidad Tecnológica del Centro (Venezuela), 2007
Work experience
- 2021–Present: Research Assistant, Simon Fraser University
- Researched information theory, learning theory, methods in representation learning and optimization
- Supervisor: Professor Ivan Bajic
- 2017–2021: Senior Data Scientist, Wattpad
- Researched deep learning methods that disentangle latent representations from unsupervised long-form text
- Developed language models for affect analysis that incorporate knowledge graph information using attention mechanisms
- Researched multilingual models to encode sentences into syntactic representations
- Researched reinforcement learning models to elicit user preferences
- Developed a Bayesian optimization engine to improve content discovery
- 2015–2017: Research Engineer, VerticalScope
- Researched and developed algorithms to quantify and predict the performance of hundreds of social networks
- Researched probabilistic graphical models in semi-supervised scenarios for language processing tasks
- 2015: Data Scientist, Terapeak
- Developed information theory algorithms to learn ontology representations from structured descriptions of products
- Created a probabilistic model to establish synonym relationships between product terms
- 2014: Research Intern, BlackBerry
- Researched temporal generative models for intrusion detection and multi-factor authentication
- 2009–2010: Software Engineer, TDA
- Developed data collection and statistical analysis platforms to derive insights
- 2004–2013: Software Engineer – Co-Founder, Web Lab
- Solved problems in content management, real estate, e-learning, human resources, messaging, and e-commerce
Skills
- High-performance scientific computing: Python, PyTorch, Numba, JAX
- Data engineering: Scala, Apache Spark, Apache Cassandra, Apache Kafka, Elasticsearch, SQL
- Backend development: Go, ZeroMQ, gRPC, Kubernetes
Awards
- NSERC Canada Graduate Scholarship – Doctoral
- Simon Fraser University Graduate Dean’s Entrance Scholarship
- Mitacs Accelerate Fellowship
Publications
Lossy common information in a learnable Gray-Wyner Network
Anderson de Andrade, Alon Harell, & Ivan Bajić. (2026). "Lossy common information in a learnable Gray-Wyner Network." ICLR.
Rate-distortion theory in coding for machines and its applications
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.
Towards task-compatible compressible representations
Anderson de Andrade, & Ivan Bajić. (2024). "Towards task-compatible compressible representations." ICME Workshop on Coding for Machines.
Base layer efficiency in scalable human-machine coding
Yalda Foroutan, Alon Harell, Anderson de Andrade, & Ivan Bajić. (2023). "Base layer efficiency in scalable human-machine coding." ICIP.
Conditional and residual methods in scalable coding for humans and machines
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.
An architecture for accelerated large-scale inference of transformer-based language models
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.
Graph representation learning network via adaptive sampling
Anderson de Andrade, & Chen Liu. (2020). "Graph representation learning network via adaptive sampling." arXiv:2006.04637.
Exploring multilingual syntactic sentence representations
Chen Liu, Anderson de Andrade, & Muhammad Osama. (2019). "Exploring multilingual syntactic sentence representations." EMNLP Workshop on Noisy User-Generated Text.
DENS: A dataset for multi-class emotion analysis
Chen Liu, Osama Muhammad, & Anderson de Andrade. (2019). "DENS: A dataset for multi-class emotion analysis." EMNLP.
Unsupervised aspect extraction from free-form conversations
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.
Best practices for convolutional neural networks applied to object recognition in images
Anderson de Andrade. (2014). "Best practices for convolutional neural networks applied to object recognition in images." arXiv:1910.13029.
A comparison of neural network training methods for text classification
Anderson de Andrade. (2013). "A comparison of neural network training methods for text classification." arXiv:1910.12674.
Talks
A machine learning research toolkit
Tutorial at School of Engineering Science, Simon Fraser University, Burnaby, BC, Canada
Towards task-compatible compressible representations
Conference proceedings talk at Niagara Falls Marriott on the Falls, Niagara Falls, ON, Canada