A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Differentiable cutting-plane layers solve parametric mixed-integer linear optimization problems.
Stochastic cutting planes improve data-driven optimization speed.
Generalizes neural network verification by adding arbitrary cutting planes.
NeuralCut learns to select cutting planes by looking ahead, outperforming traditional methods.
Improved cutting plane method for convex optimization and games.
Book covers tools for zeroth-order convex optimisation.
New algorithms solve convex optimization problems with limited memory.
Integer programming (IP) is a general optimization framework widely applicable to a variety of unstructured and structured problems arising in, e.g., scheduling, production planning, and graph optimization. As IP models many provably hard to solve problems, modern IP solvers rely on many heuristics. These heuristics ar…
This dissertation uses ILP to learn Bayesian network structures efficiently.
New memory-query tradeoffs for convex optimization algorithms.
Memory-constrained algorithms need superlinear memory for efficient convex optimization.
MOSS optimizes decision rules for accuracy and stability.
We consider the problem of classifying data manifolds where each manifold represents invariances that are parameterized by continuous degrees of freedom. Conventional data augmentation methods rely upon sampling large numbers of training examples from these manifolds; instead, we propose an iterative algorithm called M…
A Support Vector Method for multivariate performance measures was recently introduced by Joachims (2005). The underlying optimization problem is currently solved using cutting plane methods such as SVM-Perf and BMRM. One can show that these algorithms converge to an eta accurate solution in O(1/Lambda*e) iterations, wh…
Learning with non-modular losses is an important problem when sets of predictions are made simultaneously. The main tools for constructing convex surrogate loss functions for set prediction are margin rescaling and slack rescaling. In this work, we show that these strategies lead to tight convex surrogates iff the unde…
Financial portfolios are often optimized for maximum profit while subject to a constraint formulated in terms of the Conditional Value-at-Risk (CVaR). This amounts to solving a linear problem. However, in its original formulation this linear problem has a very large number of linear constraints, too many to be enforced…
New method solves complex optimization problems faster.
Paper proposes a robust method for inferring parameters in multiobjective optimization.
We study a cutting-plane method for semidefinite optimization problems (SDOs), and supply a proof of the method's convergence, under a boundedness assumption. By relating the method's rate of convergence to an initial outer approximation's diameter, we argue that the method performs well when initialized with a second-…
A new framework for sparse regression models with slow variations.
Novel method for bilevel optimization with convex lower-level problem.
New algorithm for online portfolio selection with reduced runtime.
New methods optimize complex optimization problems with improved efficiency.
We present and analyze a central cutting surface algorithm for general semi-infinite convex optimization problems, and use it to develop a novel algorithm for distributionally robust optimization problems in which the uncertainty set consists of probability distributions with given bounds on their moments. Moments of a…
We introduce an efficient method for training the linear ranking support vector machine. The method combines cutting plane optimization with red-black tree based approach to subgradient calculations, and has O(m*s+m*log(m)) time complexity, where m is the number of training examples, and s the average number of non-zer…
The area under the ROC curve (AUC) is a widely used performance measure in machine learning. Increasingly, however, in several applications, ranging from ranking to biometric screening to medicine, performance is measured not in terms of the full area under the ROC curve, but in terms of the \emph{partial} area under t…
We consider the problem of matrix completion on an matrix. We introduce the problem of Interpretable Matrix Completion that aims to provide meaningful insights for the low-rank matrix using side information. We show that the problem can be reformulated as a binary convex optimization problem. We design Opt…
The article generalizes Pearson correlation to Riemannian manifolds.
Efficiently simulates risk budgeting portfolios using novel algorithms.
Fisher score is one of the most widely used supervised feature selection methods. However, it selects each feature independently according to their scores under the Fisher criterion, which leads to a suboptimal subset of features. In this paper, we present a generalized Fisher score to jointly select features. It aims …
We consider the problem of jointly estimating the parameters as well as the structure of binary valued Markov Random Fields, in contrast to earlier work that focus on one of the two problems. We formulate the problem as a maximization of -regularized surrogate likelihood that allows us to find a sparse solution…
In this paper we study output coding for multi-label prediction. For a multi-label output coding to be discriminative, it is important that codewords for different label vectors are significantly different from each other. In the meantime, unlike in traditional coding theory, codewords in output coding are to be predic…
In this paper, a novel learning paradigm is presented to automatically identify groups of informative and correlated features from very high dimensions. Specifically, we explicitly incorporate correlation measures as constraints and then propose an efficient embedded feature selection method using recently developed cu…
This monograph presents the main complexity theorems in convex optimization and their corresponding algorithms. Starting from the fundamental theory of black-box optimization, the material progresses towards recent advances in structural optimization and stochastic optimization. Our presentation of black-box optimizati…
Generalizes leverage score sampling for neural networks, accelerating kernel methods and deep learning.
Paper solves globally optimal k-means for low dimensional data.
We present a novel binary convex reformulation of the sparse regression problem that constitutes a new duality perspective. We devise a new cutting plane method and provide evidence that it can solve to provable optimality the sparse regression problem for sample sizes n and number of regressors p in the 100,000s, that…
Complex Chern-Simons theory reveals peacock patterns in perturbative series.
We propose a unified framework to address a family of classical mixed-integer optimization problems with logically constrained decision variables, including network design, facility location, unit commitment, sparse portfolio selection, binary quadratic optimization, sparse principal analysis and sparse learning proble…
Risk scores are simple classification models that let users make quick risk predictions by adding and subtracting a few small numbers. These models are widely used in medicine and criminal justice, but are difficult to learn from data because they need to be calibrated, sparse, use small integer coefficients, and obey …
Quantum algorithms improve perceptron learning efficiency.
Quadratic memory is essential for optimal convex optimization queries.
A biclustering algorithm finds dense disjoint subgraphs in weighted bipartite graphs.
New framework for conditional risk minimization using optimal transport.
The problem of maximizing precision at the top of a ranked list, often dubbed Precision@k (prec@k), finds relevance in myriad learning applications such as ranking, multi-label classification, and learning with severe label imbalance. However, despite its popularity, there exist significant gaps in our understanding of…
Convex geometry explains optimal neural network parameters.
Paper generalizes VB-FTRL for online learning of quantum states with logarithmic loss.
We present a novel method for exact hierarchical sparse polynomial regression. Our regressor is that degree polynomial which depends on at most inputs, counting at most monomial terms, which minimizes the sum of the squares of its prediction errors. The previous hierarchical sparse specification aligns w…