Search Results for author:
Found 12 papers, 2 papers with code
Online Structured Prediction with Fenchel--Young Losses and Improved Surrogate Regret for Online Multiclass Classification with Logistic Loss
We extend the exploit-the-surrogate-gap framework to online structured prediction with \emph{Fenchel--Young losses}, a large family of surrogate losses including the logistic loss for multiclass classification, obtaining finite surrogate regret bounds in various structured prediction problems.
Data-Driven Projection for Reducing Dimensionality of Linear Programs: Generalization Bound and Learning Methods
On the theoretical side, a natural question is: how much data is sufficient to ensure the quality of recovered solutions?
Rethinking Warm-Starts with Predictions: Learning Predictions Close to Sets of Optimal Solutions for Faster $\text{L}$-/$\text{L}^\natural$-Convex Function Minimization
The main technical difficulty lies in learning predictions that are provably close to sets of all optimal solutions, for which we present an online-gradient-descent-based method.
Improved Generalization Bound and Learning of Sparsity Patterns for Data-Driven Low-Rank Approximation
Specifically, for rank-$k$ approximation using an $m \times n$ learned sketching matrix with $s$ non-zeros in each column, they proved an $\tilde{\mathrm{O}}(nsm)$ bound on the \emph{fat shattering dimension} ($\tilde{\mathrm{O}}$ hides logarithmic factors).
Lazy and Fast Greedy MAP Inference for Determinantal Point Process
One classical and practical method is the lazy greedy algorithm, which is applicable to general submodular function maximization, while a recent fast greedy algorithm based on the Cholesky factorization is more efficient for DPP MAP inference.
Sample Complexity of Learning Heuristic Functions for Greedy-Best-First and A* Search
Motivated by this emerging approach, we study the sample complexity of learning heuristic functions for GBFS and A*.
Discrete-Convex-Analysis-Based Framework for Warm-Starting Algorithms with Predictions
Augmenting algorithms with learned predictions is a promising approach for going beyond worst-case bounds.
Differentiable Equilibrium Computation with Decision Diagrams for Stackelberg Models of Combinatorial Congestion Games
We address Stackelberg models of combinatorial congestion games (CCGs); we aim to optimize the parameters of CCGs so that the selfish behavior of non-atomic players attains desirable equilibria.
Differentiable Greedy Submodular Maximization: Guarantees, Gradient Estimators, and Applications
Motivated by, e. g., sensitivity analysis and end-to-end learning, the demand for differentiable optimization algorithms has been significantly increasing.
Learning Individually Fair Classifier with Path-Specific Causal-Effect Constraint
To avoid restrictive functional assumptions, we define the {\it probability of individual unfairness} (PIU) and solve an optimization problem where PIU's upper bound, which can be estimated from data, is controlled to be close to zero.
Beyond Adaptive Submodularity: Approximation Guarantees of Greedy Policy with Adaptive Submodularity Ratio
We propose a new concept named adaptive submodularity ratio to study the greedy policy for sequential decision making.
Provable Fast Greedy Compressive Summarization with Any Monotone Submodular Function
This approach is known to have three advantages: its applicability to many useful submodular objective functions, the efficiency of the greedy algorithm, and the provable performance guarantee.
