List of things I’ve been reading. Only adding things that I’ve read thoroughly and understand beyond a superficial level.

5/18/2022

  • Curiosity-driven Exploration by Self-supervised Prediction [link]

5/17/2022

  • Adaptive Computation Time for Recurrent Neural Networks [link]

5/16/2022

  • Embodied Question Answering [link]

5/13/2022

  • Global Convergence of Non-Convex Gradient Descent for Computing Matrix Squareroot [link]

5/11/2022

  • Convolutional Dynamic Alignment Networks for Interpretable Classifications [link]
  • Optimizing for Interpretability in Deep Neural Networks with Tree Regularization [link]
  • Explainable Models with Consistent Interpretations [link]

4/27/2022

  • The Complexity of Agreement [link]
  • Superintelligence: Paths, Dangers, Strategies [link]

4/25/2022

  • Geometric Deep Learning - Grids, Groups, Graphs, Geodesics, and Gauges: Chapters 4.1, 5.3, 5.4 [link]

4/24/2022

  • Adversarial Examples Are Not Bugs, They Are Features [link]

4/23/2022

  • Image Synthesis with a Single (Robust) Classifier [link]
  • Agreeing to Disagree [link]

4/18/2022

  • Identifying Statistical Bias in Dataset Replication [link]

4/16/2022

  • What Can Neural Networks Reason About? [link]

4/15/2022

  • Cooperative Inverse Reinforcement Learning [link]
  • Editing a classifier by rewriting its prediction rules [link]

4/11/2022

  • Geometric Deep Learning - Grids, Groups, Graphs, Geodesics, and Gauges, Chapters 1-3 [link]

4/9/2022

  • The Old Man and the Sea by Ernest Hemingway

3/28/2022

  • Convergence Analysis of Two-layer Neural Networks with ReLU Activation [link]

3/7/2022

  • A Gentle Introduction to Graph Neural Networks [link]
  • A General Formula on the Conjugate of the Difference of Functions [link]
  • Generalized Convexity and Fractional Programming with Economic Applications: On Strongly Convex and Paraconvex Dualities [link]

3/5/2022

  • Group Equivariant Convolutional Networks [link]

3/2/2022

  • Model Inversion Networks for Model-Based Optimization [link]
  • Conservative Objective Models for Effective Offline Model-Based Optimization [link]

3/1/2022

  • Consequences of Misaligned AI [link]
  • Future of Life Institute AI Alignment Podcast: Inverse Reinforcement Learning and Inferring Human Preferences with Dylan Hadfield-Menell [link]

2/21/2022

  • A unified framework for Hamiltonian deep neural networks [link]
  • Stable Architectures for Deep Neural Networks [link]

2/17/2022

  • Rationality AI to Zombies: How to Actually Change Your Mind [link]
  • Generally Intelligent #10: Dylan Hadfield-Menell, UC Berkeley/MIT, on the value alignment problem in AI [link]

2/15/2022

  • Algorithms for Inverse Reinforcement Learning [link]

2/14/2022

  • Training language models to follow instructions with human feedback [link]
  • Noisy Adaptive Group Testing using Bayesian Sequential Experimental Design [link]
  • Towards a Rigorous Science of Interpretable Machine Learning [link]

2/13/2022

  • Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV) [link]
  • Concept Whitening for Interpretable Image Recognition [link]
  • NBDT: Neural-Backed Decision Trees [link]

2/12/2022

  • Rationality AI to Zombies: Map and Territory [link]

2/9/2022

  • Poincaré Embeddings for Learning Hierarchical Representations [link]

2/4/2022

  • This Looks Like That: Deep Learning for Interpretable Image Recognition [link]
  • Towards Robust Interpretability with Self-Explaining Neural Networks [link]

1/31/2022

  • A Unified Approach to Interpreting Model Predictions [link]

1/10/2022

  • Concept Bottleneck Models [link]

1/3/2022

  • Why Should I Trust You? Explaining the Predictions of Any Classifier [link]
  • How to Explain Individual Classification Decisions [link]
  • How to Explain the Prediction of a Machine Learning Model [link]

12/28/2021

  • Learning Structured Output Representation using Deep Conditional Generative Models [link]

12/27/2021

  • Genesis 1-7

12/25/2021

  • Accelerating Rescaled Gradient Descent: Fast Optimization of Smooth Functions [link]

12/23/2021

  • Tensor Algebra and Tensor Analysis for Engineers, Chapter 1: Vectors and Tensors in a Finite-Dimensional Space [link]

12/22/2021

  • Dual Space Preconditioning for Gradient Descent [link]

12/21/2021

  • Generally Intelligent #12: Jacob Steinhardt, UC Berkeley, on machine learning safety, alignment and measurement [link]

12/20/2021

  • Monte Carlo Statistical Methods, Chapter 6: Markov Chains [link]