Search Results for author:
Found 29 papers, 5 papers with code
Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
In this work, we present Tree of Attacks with Pruning (TAP), an automated method for generating jailbreaks that only requires black-box access to the target LLM.
Instance Specific Approximations for Submodular Maximization
A major question is therefore how to measure the performance of an algorithm in comparison to an optimal solution on instances we encounter in practice.
The Adaptive Complexity of Maximizing a Gross Substitutes Valuation
Both the upper and lower bounds are under the assumption that queries are only on feasible sets (i. e., of size at most k).
Investigating Gender Bias in Language Models Using Causal Mediation Analysis
As a case study, we apply this methodology to analyzing gender bias in pre-trained Transformer language models.
Adversarial Attacks on Binary Image Recognition Systems
Nevertheless, we generalize SCAR to design attacks that fool state-of-the-art check processing systems using unnoticeable perturbations that lead to misclassification of deposit amounts.
An Optimal Elimination Algorithm for Learning a Best Arm
We consider the classic problem of $(\epsilon,\delta)$-PAC learning a best arm where the goal is to identify with confidence $1-\delta$ an arm whose mean is an $\epsilon$-approximation to that of the highest mean arm in a multi-armed bandit setting.
Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias
Common methods for interpreting neural models in natural language processing typically examine either their structure or their behavior, but not both.
Robustness from Simple Classifiers
Despite the vast success of Deep Neural Networks in numerous application domains, it has been shown that such models are not robust i. e., they are vulnerable to small adversarial perturbations of the input.
The FAST Algorithm for Submodular Maximization
Recent algorithms have comparable guarantees in terms of asymptotic worst case analysis, but their actual number of rounds and query complexity depend on very large constants and polynomials in terms of precision and confidence, making them impractical for large data sets.
Predicting Choice with Set-Dependent Aggregation
Providing users with alternatives to choose from is an essential component in many online platforms, making the accurate prediction of choice vital to their success.
Robust Attacks against Multiple Classifiers
We address the challenge of designing optimal adversarial noise algorithms for settings where a learner has access to multiple classifiers.
Optimal Attacks against Multiple Classifiers
The main technical challenge we consider is the design of best response oracles that can be implemented in a Multiplicative Weight Updates framework to find equilibrium strategies in the zero-sum game.
Robust Influence Maximization for Hyperparametric Models
A recent surging research direction in influence maximization focuses on the case where the edge probabilities on the graph are not arbitrary but are generated as a function of the features of the users and a global hyperparameter.
Fast Parallel Algorithms for Statistical Subset Selection Problems
Recently, there has been a surge of interest in a parallel optimization technique called adaptive sampling which produces solutions with desirable approximation guarantees for submodular maximization in exponentially faster parallel runtime.
Optimization for Approximate Submodularity
We consider the problem of maximizing a submodular function when given access to its approximate version.
Robust Classification of Financial Risk
To the best of our knowledge, this is the first study of adversarial attacks and defenses for deep learning in financial services.
Parallelization does not Accelerate Convex Optimization: Adaptivity Lower Bounds for Non-smooth Convex Minimization
For the problem of minimizing a non-smooth convex function $f:[0, 1]^n\to \mathbb{R}$ over the unit Euclidean ball, we give a tight lower bound that shows that even when $\texttt{poly}(n)$ queries can be executed in parallel, there is no randomized algorithm with $\tilde{o}(n^{1/3})$ rounds of adaptivity that has convergence rate that is better than those achievable with a one-query-per-round algorithm.
Approximation Guarantees for Adaptive Sampling
In particular, we show that under very mild conditions of curvature of a function, adaptive sampling techniques achieve an approximation arbitrarily close to 1/2 while maintaining their low adaptivity.
Learning to Optimize Combinatorial Functions
Submodular functions have become a ubiquitous tool in machine learning.
Learning Diffusion using Hyperparameters
Despite this obstacle, we can shrink the best-known sample complexity bound for learning IC by a factor of |E|/d where |E| is the number of edges in the graph and d is the dimension of the hyperparameter.
Minimizing a Submodular Function from Samples
In this paper we consider the problem of minimizing a submodular function from training data.
Robust Guarantees of Stochastic Greedy Algorithms
In this paper we analyze the robustness of stochastic variants of the greedy algorithm for submodular maximization.
Robust Optimization for Non-Convex Objectives
We consider robust optimization problems, where the goal is to optimize in the worst case over a class of objective functions.
Maximization of Approximately Submodular Functions
We study the problem of maximizing a function that is approximately submodular under a cardinality constraint.
The Power of Optimization from Samples
In this paper we show that for any monotone submodular function with curvature c there is a (1 - c)/(1 + c - c^2) approximation algorithm for maximization under cardinality constraints when polynomially-many samples are drawn from the uniform distribution over feasible sets.
Submodular Optimization under Noise
We provide initial answers, by focusing on the question of maximizing a monotone submodular function under a cardinality constraint when given access to a noisy oracle of the function.
The Limitations of Optimization from Samples
In particular, our main result shows that there is no constant factor approximation for maximizing coverage functions under a cardinality constraint using polynomially-many samples drawn from any distribution.
Information-theoretic lower bounds for convex optimization with erroneous oracles
We consider the problem of optimizing convex and concave functions with access to an erroneous zeroth-order oracle.
Learnability of Influence in Networks
We establish PAC learnability of influence functions for three common influence models, namely, the Linear Threshold (LT), Independent Cascade (IC) and Voter models, and present concrete sample complexity results in each case.
