Framework learns linear programs from optimal decisions.
problem Learning linear programs from optimal decisions is challenging.
method Gradient-based framework for learning linear programs from optimal decisions.
result Successfully learns linear programs and multi-commodity flow instances.
Optimal binning method for numeric targets using mathematical programming.
problem Optimizing the discretization of numeric variables for classification.
method Mathematical programming formulation for binary, continuous, and multi-class targets with constraints.
result Convex mixed-integer programming formulations for all target types.
ProGraML uses graph-based machine learning to improve program optimization and analysis.
problem Improving program optimization and analysis with machine learning.
method Low-level, language agnostic graph representation and message passing neural networks.
result ProGraML achieves an average 94.0 F1 score on a benchmark dataset, significantly outperforming state-of-the-art approaches.
Adapting neural networks to guide program optimization for better classifiers.
problem Learning differentiable programs with complex architectures.
method Formulating program optimization as a graph search problem, using neural networks as heuristic relaxations.
result Trained neural networks can guide combinatorial search for programmatic classifiers, improving accuracy and interpretability.
Unified approach for optimizing predictions in linear programming and inverse problems.
problem Optimizing predictions in linear programming and inverse problems.
method Maximum optimality margin approach.
result Unified approach that balances computational efficiency and theoretical properties.
Gradient estimation techniques applied to programs with randomness in high energy physics.
problem Differentiating programs with discrete randomness in high energy physics.
method Several gradient estimation techniques, including Stochastic AD method, applied to simplified detector design experiments.
result Development of the first fully differentiable branching program.
Differentiable layers for convex optimization problems.
problem Rigidity of existing differentiable optimization layers.
method Disciplined parametrized programming and affine-solver-affine form.
result Efficient analytical differentiation through convex programs.
Novel approximation hierarchy for sparse quadratic programs.
problem Sparse Quadratic Programs with Cardinality Constraints.
method Exploits rank-dominating eigenvectors for min-max optimization over binary variables.
result Efficient screening of nonzero elements with scalable optimization algorithms.
Synthesizes static analysis for probabilistic programs.
problem Optimize learning process, verify models, improve programming interface.
method Organize and analyze static analysis techniques for probabilistic programming.
result Future directions for improvement in statistical machine learning.
This paper reviews recent advances in the field of optimization under uncertainty via a modern data lens, highlights key research challenges and promise of data-driven optimization that organically integrates machine learning and mathematical programming for decision-making under uncertainty, and identifies potential r…
Ansor generates high-performance tensor programs for deep learning.
problem Generating high-performance tensor programs for deep learning on various hardware platforms is challenging.
method Ansor uses a hierarchical representation of the search space, sampling programs, and evolutionary search with a learned cost model to find high-performance programs.
result Ansor improves deep neural network execution performance up to 3.8x on Intel CPU, 2.6x on ARM CPU, and 1.7x on NVIDIA GPU.
Paper uses integer programming for non-convex boosting in classification.
problem Improving classification performance using non-convex optimization.
method Non-convex boosting via integer programming.
result Results comparable to or better than state-of-the-art.
Data-driven optimization improves mean-variance portfolios by penalizing norms.
problem Estimation error in mean-variance optimization.
method Augment MVO with norm penalties, use neural networks for optimization, and compute derivatives implicitly.
result Data-driven optimization reduces portfolio risk compared to standard MVO.
We present a new algorithm for approximate inference in probabilistic programs, based on a stochastic gradient for variational programs. This method is efficient without restrictions on the probabilistic program; it is particularly practical for distributions which are not analytically tractable, including highly struc…
We improve optimization for data with varying variance.
problem Optimizing data with varying variance.
method Generalized learning and optimization frameworks for data-driven optimization.
result Asymptotic and finite sample guarantees for stochastic programs.
Abstract perspective on quadratic programming for optimal portfolio allocation.
problem Optimal allocation problems in long portfolio theory.
method Using maximum principles and distinguished boundaries in reproducing kernel Hilbert spaces.
result Support of an optimal distribution lies in a variety intersecting a distinguished boundary.
Defines a calculus for integrating Moreau envelopes in differentiable programming.
problem Lack of a mathematical framework for applying Moreau envelopes to deep networks and machine learning systems.
method Develops a compositional calculus adapted to Moreau envelopes and integrates it into differentiable programming.
result Integrates Moreau envelopes into differentiable programming, enabling new gradient back-propagation methods.
Paper presents an ADMM-based approach to efficiently integrate quadratic programming layers into neural networks.
problem Integrating quadratic programs into neural networks for optimization.
method An ADMM-based network layer architecture for solving quadratic programs efficiently.
result The ADMM layer is approximately an order of magnitude faster than existing methods for medium scaled problems.
New method for efficient probabilistic inference using masked language modeling.
problem Efficient posterior inference in probabilistic programs with many hyper-parameters.
method Formulate inference as masked language modeling, train a neural network to unmask random values.
result Foundation posterior for zero-shot inference and fine-tuning across a range of programs.
In this paper, we analyze dynamic programming as a novel approach to solve the problem of maximizing the profits of a bank. The mathematical model of the problem and the description of a bank's work is described in this paper. The problem is then approached using the method of dynamic programming. Dynamic programming m…
Investigates how rebalancing frequency and transaction costs affect log-optimal portfolios.
problem Impact of rebalancing frequency and transaction costs on log-optimal portfolios.
method Proved equivalence to concave program, derived optimality conditions, tested using intraday and daily data.
result Transaction costs can cause bankruptcy for frequency-dependent log-optimal portfolios, approximating to quadratic concave program.
We present the first general purpose framework for marginal maximum a posteriori estimation of probabilistic program variables. By using a series of code transformations, the evidence of any probabilistic program, and therefore of any graphical model, can be optimized with respect to an arbitrary subset of its sampled …
In this paper, we present a generic framework to extend existing uniformly optimal convex programming algorithms to solve more general nonlinear, possibly nonconvex, optimization problems. The basic idea is to incorporate a local search step (gradient descent or Quasi-Newton iteration) into these uniformly optimal conv…
DiffTaichi enables fast, differentiable physical simulations with shorter code.
problem Building efficient differentiable physical simulators.
method Differentiable programming language (DiffTaichi) that generates gradients using source code transformations and a light-weight tape.
result Differentiable physical simulators written in DiffTaichi are faster and more concise than existing methods.
Optimal Control Theory optimizes neural networks, improving robustness and efficiency.
problem Optimizing deep neural networks (DNNs) for better performance and efficiency.
method Integrating Optimal Control Theory with Backpropagation to develop a new optimizer.
result Optimal Control Theoretic Neural Optimizer (OCNOpt) improves upon existing methods in robustness and efficiency.
Optimizes intervention design for causal discovery using integer programming.
problem Identifying causal structures from observational data due to confounding variables.
method Uses integer programming to design minimal intervention sets for causal structure identifiability.
result Provides exact and modular solutions adaptable to various experimental settings and constraints.
This paper tackles multi-marginal optimal transport problems using DC programming.
problem Multi-marginal optimal transport problems in machine learning.
method Promoting structural information in MMOT leads to a DC programming problem.
result Solutions from DC optimization are as qualitative as current methods.
New method uses dynamic programming for meta continual learning.
problem Challenges of generalization and catastrophic forgetting in sequential learning.
method Developed a theoretical framework using dynamic programming for meta continual learning.
result Theoretical and practical method achieves better accuracy than existing methods.
Probabilistic programming languages (PPLs) are a powerful modeling tool, able to represent any computable probability distribution. Unfortunately, probabilistic program inference is often intractable, and existing PPLs mostly rely on expensive, approximate sampling-based methods. To alleviate this problem, one could tr…
Differentiable losses for combinatorial optimization problems in sequence modeling.
problem Mismatch between training and inference objectives in sequence models.
method Gradient descent over linear programs representing combinatorial optimization problems.
result Gradient descent can be applied to combinatorial optimization problems efficiently.
Self-taught optimizer improves code generation using language models.
problem Improving code generation using language models.
method Recursive self-improvement of a scaffolding program that generates code.
result Improved scaffolding program generates programs with significantly better performance.
Forward inference techniques such as sequential Monte Carlo and particle Markov chain Monte Carlo for probabilistic programming can be implemented in any programming language by creative use of standardized operating system functionality including processes, forking, mutexes, and shared memory. Exploiting this we have …
Method solves complex optimization problems with high probability bounds.
problem Nonlinear equality constrained stochastic optimization problems.
method Step-search sequential quadratic programming method.
result High-probability bound on iteration complexity for first-order stationarity.
New algorithm solves complex stopping problems with robust optimization.
problem Solving complex stochastic optimal stopping problems.
method Simulation-based robust optimization with exact reformulation as a zero-one bilinear program.
result Developed polynomial-time heuristics and algorithms for practical solution.
Improved genetic programming by optimizing mutation operators for continuous program search.
problem Small syntactic mutations in genetic programming can lead to unpredictable behavioral shifts.
method Learned a compact trading-strategy DSL, created a block-factorized embedding, and designed geometry-compiled mutation operators.
result Geometry-compiled mutation operators discover strong strategies using fewer evaluations and achieve higher Sharpe ratios.
Solving linear programs by using entropic penalization has recently attracted new interest in the optimization community, since this strategy forms the basis for the fastest-known algorithms for the optimal transport problem, with many applications in modern large-scale machine learning. Crucial to these applications h…
In this work, we explore how probabilistic programs can be used to represent policies in sequential decision problems. In this formulation, a probabilistic program is a black-box stochastic simulator for both the problem domain and the agent. We relate classic policy gradient techniques to recently introduced black-box…
A new approach for specifying and synthesizing subroutines for optimizing metrics.
problem Specifying and optimizing subroutines for various metrics.
method Formalizing programming by rewards (PBR), using continuous-optimization techniques to synthesize decision functions as if-then-else programs.
result Synthesized decision functions are optimal in cases when rewards have nice properties.
We extend an approach of Beliakova for computing knot Floer homology and implement it in a publicly available computer program. We review the main programming and optimization methods used. Our program is then used to check that the Floer homology of a prime non-alternating knot with less than 12 crossings has no torsi…
Paper proposes algorithms for BMF using integer programming.
problem Approximating binary input matrix as product of two smaller binary factors.
method Alternating optimization strategy using integer programming to solve subproblems and combine solutions.
result Proposed algorithms outperform state of the art on medium-scale problems.
Develops new optimization techniques for decision-making under uncertainty.
problem Decision-making under uncertainty with complex cost functions and nested expectations.
method Introduces Multistage Conditional Compositional Optimization (MCCO) and develops multilevel Monte Carlo techniques.
result New optimization techniques reduce scenario complexity from exponential to polynomial growth.
We study the problem of instance segmentation in biological images with crowded and compact cells. We formulate this task as an integer program where variables correspond to cells and constraints enforce that cells do not overlap. To solve this integer program, we propose a column generation formulation where the prici…
This study optimizes cycle representatives in persistent homology using linear programming.
problem Non-uniqueness of cycle representatives in persistent homology creates ambiguity.
method Optimization of cycle representatives using linear programming methods.
result Optimization reduces the size of cycle representatives and is effective in most data sets.
Bayesian optimization tackles non-convex, two-stage stochastic problems efficiently.
problem Solving non-convex, two-stage stochastic optimization problems with expensive, black-box evaluations.
method Knowledge-gradient-based acquisition function for joint optimization of first- and second-stage variables.
result Comparable and superior empirical results compared to alternatives.
Extends DCP framework to Hadamard manifolds for geodesically convex functions.
problem Verifying convexity in nonlinear programs on Hadamard manifolds.
method Introduces Disciplined Geodesically Convex Programming (DGCP) framework, defining compositions and transformations for geodesically convex functions.
result Allows verification of geodesic convexity for a broader range of functions, including statistical estimators and matrix-valued optimization.
Unified framework for learning flexible probabilistic programs using DPP and PAC-Bayes bounds.
problem Learning and generalizing from complex probabilistic models.
method Unified DPP representation and PAC-Bayes bounds for stochastic programs.
result Improved performance and generalization prediction using flexible DPP model representations and learned complexity measures.
Convex optimization method infers latent structure in random dot product graphs.
problem Inferring latent probability matrix of random dot product graphs.
method Conic programming with nuclear norm regularization.
result Asymptotic consistency of probability estimates and recovery of latent structure.
SOS programming verifies MTW tensor non-negativity for optimal transport maps.
problem Verifying MTW tensor non-negativity for general cost functions is difficult.
method Sum-of-Squares (SOS) programming for verifying and approximating MTW non-negativity.
result SOS programming provides certificates and approximations of MTW non-negativity.