Corpus ID: 209515681

Model Inversion Networks for Model-Based Optimization

@article{Kumar2020ModelIN,
  title={Model Inversion Networks for Model-Based Optimization},
  author={Aviral Kumar and Sergey Levine},
  journal={ArXiv},
  year={2020},
  volume={abs/1912.13464}
}
In this work, we aim to solve data-driven optimization problems, where the goal is to find an input that maximizes an unknown score function given access to a dataset of inputs with corresponding scores. When the inputs are high-dimensional and valid inputs constitute a small subset of this space (e.g., valid protein sequences or valid natural images), such model-based optimization problems become exceptionally difficult, since the optimizer must avoid out-of-distribution and invalid inputs. We… Expand
Offline Model-Based Optimization via Normalized Maximum Likelihood Estimation
TLDR
This work proposes to tackle data-driven optimization problems where one must maximize a function given only queries at a fixed set of points by leveraging the normalized maximum-likelihood (NML) estimator, which provides a principled approach to handling uncertainty and out-of-distribution inputs. Expand
Conservative Objective Models for Effective Offline Model-Based Optimization
TLDR
Conservative objective models (COMs) are proposed, a method that learns a model of the objective function which lower bounds the actual value of the ground-truth objective on outof-distribution inputs and uses it for optimization. Expand
MALIZED MAXIMUM LIKELIHOOD ESTIMATION
In this work we consider data-driven optimization problems where one must maximize a function given only queries at a fixed set of points. This problem setting emerges in many domains where functionExpand
Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization
Black-box model-based optimization (MBO) problems, where the goal is to find 1 a design input that maximizes an unknown objective function, are ubiquitous 2 in a wide range of domains, such as theExpand
Effective Surrogate Models for Protein Design with Bayesian Optimization
Bayesian optimization, which uses a probabilistic surrogate for an expensive black-box function, provides a framework for protein design that requires a small amount of labeled data. In this paper,Expand
Deep Extrapolation for Attribute-Enhanced Generation
Attribute extrapolation in sample generation is challenging for deep neural networks operating beyond the training distribution. We formulate a new task for extrapolation in sequence generation,Expand
Advances in machine learning for directed evolution.
TLDR
Advances in ML approaches that use ML models trained on sequences to generate new functional sequence diversity are highlighted, focusing on strategies that use these generative models to efficiently explore vast regions of protein space. Expand
Adaptive machine learning for protein engineering
TLDR
This work reviews how to use a sequence-to-function machine-learning surrogate model to select sequences for experimental measurement and discusses sequential optimization, where the goal is to discover optimized sequences and improve the model across multiple rounds of training, optimization, and experimental measurement. Expand
A primer on model-guided exploration of fitness landscapes for biological sequence design
TLDR
This primer can serve as a starting point for researchers from different domains that are interested in the problem of searching a sequence space with a model, but are perhaps unaware of approaches that originate outside their field. Expand
Artificial intelligence in early drug discovery enabling precision medicine
TLDR
For learning how the development of drugs can be tailored to the heterogeneity of patients across their molecular profiles, artificial intelligence algorithms are the next frontier in precision medicine and will enable a fully personalized approach in drug design and thus ultimately impacting clinical practice. Expand
...
1
2
...

References

SHOWING 1-10 OF 56 REFERENCES
Scalable Bayesian Optimization Using Deep Neural Networks
TLDR
This work shows that performing adaptive basis function regression with a neural network as the parametric form performs competitively with state-of-the-art GP-based approaches, but scales linearly with the number of data rather than cubically, which allows for a previously intractable degree of parallelism. Expand
Conditioning by adaptive sampling for robust design
TLDR
This work proposes a new method, Conditioning by Adaptive Sampling, which yields state-of-the-art results on a protein fluorescence problem, as compared to other recently published approaches. Expand
Neural Processes
TLDR
This work introduces a class of neural latent variable models which it calls Neural Processes (NPs), combining the best of both worlds: probabilistic, data-efficient and flexible, however they are also computationally intensive and thus limited in their applicability. Expand
Neural Architecture Search with Reinforcement Learning
TLDR
This paper uses a recurrent network to generate the model descriptions of neural networks and trains this RNN with reinforcement learning to maximize the expected accuracy of the generated architectures on a validation set. Expand
Auto-Encoding Variational Bayes
TLDR
A stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case is introduced. Expand
Conditional Neural Processes
TLDR
Conditional Neural Processes are inspired by the flexibility of stochastic processes such as GPs, but are structured as neural networks and trained via gradient descent, yet scale to complex functions and large datasets. Expand
Attentive Neural Processes
TLDR
Attention is incorporated into NPs, allowing each input location to attend to the relevant context points for the prediction, which greatly improves the accuracy of predictions, results in noticeably faster training, and expands the range of functions that can be modelled. Expand
Practical Bayesian Optimization of Machine Learning Algorithms
TLDR
This work describes new algorithms that take into account the variable cost of learning algorithm experiments and that can leverage the presence of multiple cores for parallel experimentation and shows that these proposed algorithms improve on previous automatic procedures and can reach or surpass human expert-level optimization for many algorithms. Expand
Density estimation using Real NVP
TLDR
This work extends the space of probabilistic models using real-valued non-volume preserving (real NVP) transformations, a set of powerful invertible and learnable transformations, resulting in an unsupervised learning algorithm with exact log-likelihood computation, exact sampling, exact inference of latent variables, and an interpretable latent space. Expand
Model-based reinforcement learning for biological sequence design
TLDR
A model-based variant of PPO, DyNA-PPO, is proposed to improve sample efficiency and performs significantly better than existing methods in settings in which modeling is feasible, while still not performing worse in situations in which a reliable model cannot be learned. Expand
...
1
2
3
4
5
...