Efficient and modular implicit differentiation
Automatic differentiation (autodiff) has revolutionized machine learning. Itallows to express
complex computations by composing elementary ones in creativeways and removes the …
complex computations by composing elementary ones in creativeways and removes the …
Differentiable convex optimization layers
Recent work has shown how to embed differentiable optimization problems (that is,
problems whose solutions can be backpropagated through) as layers within deep learning …
problems whose solutions can be backpropagated through) as layers within deep learning …
Global planning for contact-rich manipulation via local smoothing of quasi-dynamic contact models
The empirical success of reinforcement learning (RL) in contact-rich manipulation leaves
much to be understood from a model-based perspective, where the key difficulties are often …
much to be understood from a model-based perspective, where the key difficulties are often …
Deep declarative networks
We explore a class of end-to-end learnable models wherein data processing nodes (or
network layers) are defined in terms of desired behavior rather than an explicit forward …
network layers) are defined in terms of desired behavior rather than an explicit forward …
Convex optimization algorithms in medical image reconstruction—in the age of AI
The past decade has seen the rapid growth of model based image reconstruction (MBIR)
algorithms, which are often applications or adaptations of convex optimization algorithms …
algorithms, which are often applications or adaptations of convex optimization algorithms …
Interior point solving for lp-based prediction+ optimisation
Solving optimization problem is the key to decision making in many real-life analytics
applications. However, the coefficients of the optimization problems are often uncertain and …
applications. However, the coefficients of the optimization problems are often uncertain and …
Comboptnet: Fit the right np-hard problem by learning integer programming constraints
Bridging logical and algorithmic reasoning with modern machine learning techniques is a
fundamental challenge with potentially transformative impact. On the algorithmic side, many …
fundamental challenge with potentially transformative impact. On the algorithmic side, many …
[HTML][HTML] More than accuracy: end-to-end wind power forecasting that optimises the energy system
Weather forecast models are essential for sustainable energy systems. However, forecast
accuracy may not be the best metric for developing forecast models. A more or less …
accuracy may not be the best metric for developing forecast models. A more or less …
Surco: Learning linear surrogates for combinatorial nonlinear optimization problems
Optimization problems with nonlinear cost functions and combinatorial constraints appear in
many real-world applications but remain challenging to solve efficiently compared to their …
many real-world applications but remain challenging to solve efficiently compared to their …
Deepemd: Differentiable earth mover's distance for few-shot learning
In this work, we develop methods for few-shot image classification from a new perspective of
optimal matching between image regions. We employ the Earth Mover's Distance (EMD) as …
optimal matching between image regions. We employ the Earth Mover's Distance (EMD) as …