Summaries and annotations of research papers across broad spectrum of AI and ML.

✔️ indicates that summary is available.

Monotonicity in Neural Networks

• IEEE, 1993: Learning bias in neural networks and an approach to controlling its effect in monotonic classification
• Decision Sciences, 1993: Application of the Back Propagation Neural Network Algorithm with Monotonicity Constraints for Two‐Group Classification Problems
• Neural Computing & Applications, 1994: A neural network method of density estimation for univariate unimodal data
• NIPS, 1997: Monotonic Networks
• NIPS, 1997: Monotonicity Hints
• Neural Computing & Applications, 1999: Application of MLP Networks to Bond Rating and House Pricing
• Springer, 1999: Neural Networks for Two-Group Classification Problems with Monotonicity Hints
• ICANN, 2005: Monotonic Multi-layer Perceptron Networks as Universal Approximators
• PhD Thesis (Velikova, 2006): Monotone models for prediction in data mining
• ICANN, 2008: Comparison of Neural Networks Incorporating Partial Monotonicity by Structure
• IEEE, 2010: Monotone and Partially Monotone Neural Networks
• Neural Networks, 2010: Comparison of universal approximators incorporating partial monotonicity by structure
• JMLR, 2016: Monotonic Calibrated Interpolated Look-Up Tables
• NIPS, 2016: Fast and Flexible Monotonic Functions with Ensembles of Lattices
• NIPS, 2017: Deep Lattice Networks and Partial Monotonic Functions
• Neurocomputing, 2017: Monotonic classification extreme learning machine
• NeurIPS, 2019: Unconstrained Monotonic Neural Networks
• Neurocomputing, 2019: Monotonic classification: An overview on algorithms, performance measures and data sets
• arXiv, 2019: MonoNet: Towards Interpretable Models by Learning Monotonic Features
• NeurIPS Workshop, 2019: How to Incorporate Monotonicity in Deep Networks While Preserving Flexibility?
• AISTATS, 2020: Deontological Ethics By Monotonicity Shape Constraints (Annotated) ✔️

Reinforcement Learning

• ICML 1993: Multi-Agent Reinforcement Learning: Independent vs. Cooperative Agents ✔️
• NIPS, 2010: Double Q-learning (Annotated)
• NIPS Workshop, 2013: Playing Atari with Deep Reinforcement Learning (Annotated)

Applications

• ICML Workshop, 2019: Autonomous Airline Revenue Management: A Deep Reinforcement Learning Approach to Seat Inventory Control and Overbooking (Annotated)

Federated Learning

• arXiv, 2019: Advances and Open Problems in Federated Learning

Optimization

• AISTATS, 2017: Communication-Efficient Learning of Deep Networks from Decentralized Data (Annotated)
• arXiv, 2018: Federated Learning with Non-IID Data (Annotated)
• arXiv, 2019: Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification (Annotated)
• arXiv, 2019: SCAFFOLD: Stochastic Controlled Averaging for Federated Learning (Annotated)
• arXiv, 2019: Accelerating Federated Learning via Momentum Gradient Descent
• NeurIPS Workshop, 2019: Overcoming Forgetting in Federated Learning on Non-IID Data
• arXiv, 2020: Faster On-Device Training Using New Federated Momentum Algorithm
• MLSys, 2020: Federated Optimization in Heterogeneous Networks (Annotated)
• arXiv, 2020: Adaptive Federated Optimization (Annotated)
• ICLR, 2020: On the Convergence of FedAvg on Non-IID Data