About
Categories
Advisors
Talks
Papers
Interests
Work Experiences
2024 A baby and a PhD
2023 Taking a break from NLP Research
2022 You don't feel like you're good enough, but its not a competition
2021 You're not doing well, but motivation is optional
2018 From psychologist to CS PhD Student
2017 Communicating Data Science
2017 Cross disciplinary projects
2015 DSO Advice
Bayesian Inference
2022 Stochastic Gradient Langevin Dynamics
2022 Minimum Bayes Risk Decoding
2019 Coordinate Ascent Mean-field Variational Inference (Univariate Gaussian Example)
2019 Dirichlet Process Gaussian Mixture Models (Generation)
2017 Gibbs Sampling on Dirichlet Multinomial Naive Bayes (Text)
2017 Markov Chain Monte-Carlo
2017 EM Algorithm for Gaussian mixtures
2017 Conjugate Priors
2017 Closed form Bayesian Inference for Binomial distributions
Misc
2024 Vibe Coding Car Racing Simulator (Fail)
2024 First 100 words
2022 Could Large Language Models be conscious? (David Chalmers @ Neurips 2022)
2022 NYCMidnight-100words
2020 Adversarial NLP examples with Fast Gradient Sign Method
2019 Modes of Convergence
2018 Algorithms on Graphs: Fastest Route
Machine Learning
2023 Training Sparse Neural Networks with L0 Regularisation
2022 Stochastic Gradient Langevin Dynamics
2021 Formalising Analogies for A.I
2021 Likelihood weighted Sequential Importance Sampling
2020 Some QA from Deep Learning (CS 462/482)
2020 Variance of the Estimator in Machine Learning
2020 The Sigmoid in Regression, Neural Network Activation and LSTM Gates
2019 Coordinate Ascent Mean-field Variational Inference (Univariate Gaussian Example)
2018 Onboarding for Practical Machine Learning Research
2018 Jacobian, Chain rule and backpropagation
2018 Gradients, partial derivatives, directional derivatives, and gradient descent
2018 Calculus for Machine Learning
Calculus
2018 PyTorch Automatic differentiation for non-scalar variables; Reconstructing the Jacobian
2018 Lagrange Multipliers and Constrained Optimization
2018 Taylor Series approximation, newton's method and optimization
2018 Hessian, second order derivatives, convexity, and saddle points
2018 Jacobian, Chain rule and backpropagation
2018 Gradients, partial derivatives, directional derivatives, and gradient descent
2018 Derivatives, differentiability and loss functions
2018 Calculus for Machine Learning
Optimization
2022 Stochastic Gradient Langevin Dynamics
2018 Equivalence of constrained and unconstrained form for Ridge Regression
2018 Lagrange Multipliers and Constrained Optimization
2018 Taylor Series approximation, newton's method and optimization
2018 Gradients, partial derivatives, directional derivatives, and gradient descent
Code
2025 Dynamic Batching for Training Large Sequence Models (LLMs)
2024 Vibe Coding Car Racing Simulator (Fail)
2024 Chunking code for RAG; parsing-recursion-stack
2024 Python Decorators for Monitoring GPU Usage
2023 Monitoring Jobs on the Server
2023 Lean OmegaConf Argparse System
2022 Recipe for connecting to Google Drive from Remote Server
2020 A minimum keystroke (py)Debugger for Lazy ML/DS people who don't IDE
2020 Recipe for building jq from source without admin(sudo) rights
2018 Gotchas in Cython; Handling numpy arrays in cython class
2018 Migrating from python 2.7 to python 3 (and maintaining compatibility)
Projects
2025 RAG System Architecture
2024 Data Extraction for Unstructured Document Data
2020 A minimum keystroke (py)Debugger for Lazy ML/DS people who don't IDE
2018 Studying drug-drug interactions and predictors of adverse vascular outcomes
2018 Capturing Last-mile Transactions of Smallholder Palm Oil Farmers
PyTorch
2025 Dynamic Batching for Training Large Sequence Models (LLMs)
2024 Python Decorators for Monitoring GPU Usage
2019 Clean TreeLSTMs implementation in PyTorch using NLTK treepositions and Easy-First Parsing
2019 Pad pack sequences for Pytorch batch processing with DataLoader
2018 PyTorch Automatic differentiation for non-scalar variables; Reconstructing the Jacobian
Review
2022 NLP Papers at ICML2022
2021 Neural Tangent Kernel, Every Model trained by GD is a kernel machine (Review)
2020 NEURIPS 2020
2020 EMNLP 2020
2020 Some Clustering Papers at ICLR20
2019 Arithmetic(Book)
Machine Translation
2022 Minimum Bayes Risk Decoding
Reinforcement Learning
2024 Deriving the Basic Policy Gradient Update (REINFORCE)
2024 Temporal Difference Learning: Taking advantage of Incomplete Trajectories
2023 Dynamic Programming for Reinforcement Learning, the importance of the Bellman equations; (with Gymnasium)
Compression
2023 Training Sparse Neural Networks with L0 Regularisation
Generative Models
2024 Deriving the minimax equation for GANs
2024 A classical NLP researcher and a GPT-era Engineer meet at the coffee machine
2023 LLM Research and Adaptation Landscape
NLP
2024 Synthetic Question Generation for Retrieval Evaluation of RAG