arXiv subjects

Ramtin Pedarsani

Publications and source records attributed to Ramtin Pedarsani.

At least 37 records · Page 2Linked to original sources

arXiv2024

Inverse Reinforcement Learning by Estimating Expertise of Demonstrators

In Imitation Learning (IL), utilizing suboptimal and heterogeneous demonstrations presents a substantial challenge due to the varied nature of real-world data. However, standard IL algorithms consider these datasets as homogeneous, thereby inheriting the deficiencies of suboptimal demonstrators. Previous approaches to this issue rely on impractical assumptions like high-quality data subsets, confidence rankings, or explicit environmental knowledge. This paper introduces IRLEED, Inverse Reinforcement Learning by Estimating Expertise of Demonstrators, a novel framework that overcomes these hurdles without prior knowledge of demonstrator expertise. IRLEED enhances existing Inverse Reinforcement Learning (IRL) algorithms by combining a general model for demonstrator suboptimality to address reward bias and action variance, with a Maximum Entropy IRL framework to efficiently derive the optimal policy from diverse, suboptimal demonstrations. Experiments in both online and offline IL settings, with simulated and human-generated data, demonstrate IRLEED's adaptability and effectiveness, making it a versatile solution for learning from suboptimal demonstrations.

cs.LG↗

arXiv2024

No Free Lunch for Defending Against Prefilling Attack by In-Context Learning

The security of Large Language Models (LLMs) has become an important research topic since the emergence of ChatGPT. Though there have been various effective methods to defend against jailbreak attacks, prefilling attacks remain an unsolved and popular threat against open-sourced LLMs. In-Context Learning (ICL) offers a computationally efficient defense against various jailbreak attacks, yet no effective ICL methods have been developed to counter prefilling attacks. In this paper, we: (1) show that ICL can effectively defend against prefilling jailbreak attacks by employing adversative sentence structures within demonstrations; (2) characterize the effectiveness of this defense through the lens of model size, number of demonstrations, over-defense, integration with other jailbreak attacks, and the presence of safety alignment. Given the experimental results and our analysis, we conclude that there is no free lunch for defending against prefilling jailbreak attacks with ICL. On the one hand, current safety alignment methods fail to mitigate prefilling jailbreak attacks, but adversative structures within ICL demonstrations provide robust defense across various model sizes and complex jailbreak attacks. On the other hand, LLMs exhibit similar over-defensiveness when utilizing ICL demonstrations with adversative structures, and this behavior appears to be independent of model size.

cs.CR↗

arXiv2024

Pricing for Multi-modal Pickup and Delivery Problems with Heterogeneous Users

In this paper, we study the pickup and delivery problem with multiple transportation modalities, and address the challenge of efficiently allocating transportation resources while price matching users with their desired delivery modes. More precisely, we consider that orders are demanded by a heterogeneous population of users with varying trade-offs between price and latency. To capture how prices affect the behavior of heterogeneous selfish users choosing between multiple delivery modes, we construct a congestion game taking place over a form of star network, where each source-sink pair is composed of parallel links connecting users with their preferred delivery method. Using the unique geometry of this network, we prove that one can set prices explicitly to induce any desired network flow, i.e, given a desired allocation strategy, we have a closed-form solution for the delivery prices. We conclude by performing a case study on a meal delivery problem with multiple courier modalities using data from real world instances.

eess.SY↗

arXiv2024

Conflict-Aware Adversarial Training

Adversarial training is the most effective method to obtain adversarial robustness for deep neural networks by directly involving adversarial samples in the training procedure. To obtain an accurate and robust model, the weighted-average method is applied to optimize standard loss and adversarial loss simultaneously. In this paper, we argue that the weighted-average method does not provide the best tradeoff for the standard performance and adversarial robustness. We argue that the failure of the weighted-average method is due to the conflict between the gradients derived from standard and adversarial loss, and further demonstrate such a conflict increases with attack budget theoretically and practically. To alleviate this problem, we propose a new trade-off paradigm for adversarial training with a conflict-aware factor for the convex combination of standard and adversarial loss, named \textbf{Conflict-Aware Adversarial Training~(CA-AT)}. Comprehensive experimental results show that CA-AT consistently offers a superior trade-off between standard performance and adversarial robustness under the settings of adversarial training from scratch and parameter-efficient finetuning.

cs.LG↗

arXiv2024

Long-Term Fairness in Sequential Multi-Agent Selection with Positive Reinforcement

While much of the rapidly growing literature on fair decision-making focuses on metrics for one-shot decisions, recent work has raised the intriguing possibility of designing sequential decision-making to positively impact long-term social fairness. In selection processes such as college admissions or hiring, biasing slightly towards applicants from under-represented groups is hypothesized to provide positive feedback that increases the pool of under-represented applicants in future selection rounds, thus enhancing fairness in the long term. In this paper, we examine this hypothesis and its consequences in a setting in which multiple agents are selecting from a common pool of applicants. We propose the Multi-agent Fair-Greedy policy, that balances greedy score maximization and fairness. Under this policy, we prove that the resource pool and the admissions converge to a long-term fairness target set by the agents when the score distributions across the groups in the population are identical. We provide empirical evidence of existence of equilibria under non-identical score distributions through synthetic and adapted real-world datasets. We then sound a cautionary note for more complex applicant pool evolution models, under which uncoordinated behavior by the agents can cause negative reinforcement, leading to a reduction in the fraction of under-represented applicants. Our results indicate that, while positive reinforcement is a promising mechanism for long-term fairness, policies must be designed carefully to be robust to variations in the evolution model, with a number of open issues that remain to be explored by algorithm designers, social scientists, and policymakers.

stat.ML↗

arXiv2024

Learning to Understand: Identifying Interactions via the Möbius Transform

One of the key challenges in machine learning is to find interpretable representations of learned functions. The Möbius transform is essential for this purpose, as its coefficients correspond to unique importance scores for sets of input variables. This transform is closely related to widely used game-theoretic notions of importance like the Shapley and Bhanzaf value, but it also captures crucial higher-order interactions. Although computing the obius Transform of a function with $n$ inputs involves $2^n$ coefficients, it becomes tractable when the function is sparse and of low-degree as we show is the case for many real-world functions. Under these conditions, the complexity of the transform computation is significantly reduced. When there are $K$ non-zero coefficients, our algorithm recovers the Möbius transform in $O(Kn)$ samples and $O(Kn^2)$ time asymptotically under certain assumptions, the first non-adaptive algorithm to do so. We also uncover a surprising connection between group testing and the Möbius transform. For functions where all interactions involve at most $t$ inputs, we use group testing results to compute the Möbius transform with $O(Kt\log n)$ sample complexity and $O(K\mathrm{poly}(n))$ time. A robust version of this algorithm withstands noise and maintains this complexity. This marks the first $n$ sub-linear query complexity, noise-tolerant algorithm for the Möbius transform. In several examples, we observe that representations generated via sparse Möbius transform are up to twice as faithful to the original function, as compared to Shaply and Banzhaf values, while using the same number of terms.

cs.LG↗

arXiv2024

Generalization Properties of Adversarial Training for $\ell_0$-Bounded Adversarial Attacks

We have widely observed that neural networks are vulnerable to small additive perturbations to the input causing misclassification. In this paper, we focus on the $\ell_0$-bounded adversarial attacks, and aim to theoretically characterize the performance of adversarial training for an important class of truncated classifiers. Such classifiers are shown to have strong performance empirically, as well as theoretically in the Gaussian mixture model, in the $\ell_0$-adversarial setting. The main contribution of this paper is to prove a novel generalization bound for the binary classification setting with $\ell_0$-bounded adversarial perturbation that is distribution-independent. Deriving a generalization bound in this setting has two main challenges: (i) the truncated inner product which is highly non-linear; and (ii) maximization over the $\ell_0$ ball due to adversarial training is non-convex and highly non-smooth. To tackle these challenges, we develop new coding techniques for bounding the combinatorial dimension of the truncated hypothesis class.

cs.LG↗

arXiv2024

The Fair Value of Data Under Heterogeneous Privacy Constraints in Federated Learning

Modern data aggregation often involves a platform collecting data from a network of users with various privacy options. Platforms must solve the problem of how to allocate incentives to users to convince them to share their data. This paper puts forth an idea for a \textit{fair} amount to compensate users for their data at a given privacy level based on an axiomatic definition of fairness, along the lines of the celebrated Shapley value. To the best of our knowledge, these are the first fairness concepts for data that explicitly consider privacy constraints. We also formulate a heterogeneous federated learning problem for the platform with privacy level options for users. By studying this problem, we investigate the amount of compensation users receive under fair allocations with different privacy levels, amounts of data, and degrees of heterogeneity. We also discuss what happens when the platform is forced to design fair incentives. Under certain conditions we find that when privacy sensitivity is low, the platform will set incentives to ensure that it collects all the data with the lowest privacy options. When the privacy sensitivity is above a given threshold, the platform will provide no incentives to users. Between these two extremes, the platform will set the incentives so some fraction of the users chooses the higher privacy option and the others chooses the lower privacy option.

cs.LG↗

arXiv2023

Equal Improvability: A New Fairness Notion Considering the Long-term Impact

Devising a fair classifier that does not discriminate against different groups is an important problem in machine learning. Although researchers have proposed various ways of defining group fairness, most of them only focused on the immediate fairness, ignoring the long-term impact of a fair classifier under the dynamic scenario where each individual can improve its feature over time. Such dynamic scenarios happen in real world, e.g., college admission and credit loaning, where each rejected sample makes effort to change its features to get accepted afterwards. In this dynamic setting, the long-term fairness should equalize the samples' feature distribution across different groups after the rejected samples make some effort to improve. In order to promote long-term fairness, we propose a new fairness notion called Equal Improvability (EI), which equalizes the potential acceptance rate of the rejected samples across different groups assuming a bounded level of effort will be spent by each rejected sample. We analyze the properties of EI and its connections with existing fairness notions. To find a classifier that satisfies the EI requirement, we propose and study three different approaches that solve EI-regularized optimization problems. Through experiments on both synthetic and real datasets, we demonstrate that the proposed EI-regularized algorithms encourage us to find a fair classifier in terms of EI. Finally, we provide experimental results on dynamic scenarios which highlight the advantages of our EI metric in achieving the long-term fairness. Codes are available in a GitHub repository, see https://github.com/guldoganozgur/ei_fairness.

cs.LG↗

arXiv2022

Learning-based social coordination to improve safety and robustness of cooperative autonomous vehicles in mixed traffic

It is expected that autonomous vehicles(AVs) and heterogeneous human-driven vehicles(HVs) will coexist on the same road. The safety and reliability of AVs will depend on their social awareness and their ability to engage in complex social interactions in a socially accepted manner. However, AVs are still inefficient in terms of cooperating with HVs and struggle to understand and adapt to human behavior, which is particularly challenging in mixed autonomy. In a road shared by AVs and HVs, the social preferences or individual traits of HVs are unknown to the AVs and different from AVs, which are expected to follow a policy, HVs are particularly difficult to forecast since they do not necessarily follow a stationary policy. To address these challenges, we frame the mixed-autonomy problem as a multi-agent reinforcement learning (MARL) problem and propose an approach that allows AVs to learn the decision-making of HVs implicitly from experience, account for all vehicles' interests, and safely adapt to other traffic situations. In contrast with existing works, we quantify AVs' social preferences and propose a distributed reward structure that introduces altruism into their decision-making process, allowing the altruistic AVs to learn to establish coalitions and influence the behavior of HVs.

cs.RO↗

arXiv2022

Imitation Learning by Estimating Expertise of Demonstrators

Many existing imitation learning datasets are collected from multiple demonstrators, each with different expertise at different parts of the environment. Yet, standard imitation learning algorithms typically treat all demonstrators as homogeneous, regardless of their expertise, absorbing the weaknesses of any suboptimal demonstrators. In this work, we show that unsupervised learning over demonstrator expertise can lead to a consistent boost in the performance of imitation learning algorithms. We develop and optimize a joint model over a learned policy and expertise levels of the demonstrators. This enables our model to learn from the optimal behavior and filter out the suboptimal behavior of each demonstrator. Our model learns a single policy that can outperform even the best demonstrator, and can be used to estimate the expertise of any demonstrator at any state. We illustrate our findings on real-robotic continuous control tasks from Robomimic and discrete environments such as MiniGrid and chess, out-performing competing methods in $21$ out of $23$ settings, with an average of $7\%$ and up to $60\%$ improvement in terms of the final reward.

cs.LG↗

arXiv2022

Congestion-aware Bi-modal Delivery Systems Utilizing Drones

Bi-modal delivery systems are a promising solution to the challenges posed by the increasing demand of e-commerce. Due to the potential benefit drones can have on logistics networks such as delivery systems, some countries have taken steps towards integrating drones into their airspace. In this paper we aim to quantify this potential by developing a mathematical model for a Bi-modal delivery system composed of trucks and drones. We propose an optimization formulation that can be efficiently solved in order to design socially-optimal routing and allocation policies. We incorporate both societal cost in terms of road congestion and parcel delivery latency in our formulation. Our model is able to quantify the effect drones have on mitigating road congestion, and can solve for the path routing needed to minimize the chosen objective. To accurately capture the effect of stopping trucks on road latency, we model it using SUMO by simulating roads shared by trucks and cars. Based on this, we show that the proposed framework is computationally feasible to scale due to its reliance on convex quadratic optimization techniques.

math.OC↗

arXiv2022

An Optimal Transport Approach to Personalized Federated Learning

Federated learning is a distributed machine learning paradigm, which aims to train a model using the local data of many distributed clients. A key challenge in federated learning is that the data samples across the clients may not be identically distributed. To address this challenge, personalized federated learning with the goal of tailoring the learned model to the data distribution of every individual client has been proposed. In this paper, we focus on this problem and propose a novel personalized Federated Learning scheme based on Optimal Transport (FedOT) as a learning algorithm that learns the optimal transport maps for transferring data points to a common distribution as well as the prediction model under the applied transport map. To formulate the FedOT problem, we extend the standard optimal transport task between two probability distributions to multi-marginal optimal transport problems with the goal of transporting samples from multiple distributions to a common probability domain. We then leverage the results on multi-marginal optimal transport problems to formulate FedOT as a min-max optimization problem and analyze its generalization and optimization properties. We discuss the results of several numerical experiments to evaluate the performance of FedOT under heterogeneous data distributions in federated learning problems.

cs.LG↗

arXiv2022

Straggler-Resilient Personalized Federated Learning

Federated Learning is an emerging learning paradigm that allows training models from samples distributed across a large network of clients while respecting privacy and communication restrictions. Despite its success, federated learning faces several challenges related to its decentralized nature. In this work, we develop a novel algorithmic procedure with theoretical speedup guarantees that simultaneously handles two of these hurdles, namely (i) data heterogeneity, i.e., data distributions can vary substantially across clients, and (ii) system heterogeneity, i.e., the computational power of the clients could differ significantly. Our method relies on ideas from representation learning theory to find a global common representation using all clients' data and learn a user-specific set of parameters leading to a personalized solution for each client. Furthermore, our method mitigates the effects of stragglers by adaptively selecting clients based on their computational characteristics and statistical significance, thus achieving, for the first time, near optimal sample complexity and provable logarithmic speedup. Experimental results support our theoretical findings showing the superiority of our method over alternative personalized federated schemes in system and data heterogeneous environments.

cs.LG↗

arXiv2022

Social Coordination and Altruism in Autonomous Driving

Despite the advances in the autonomous driving domain, autonomous vehicles (AVs) are still inefficient and limited in terms of cooperating with each other or coordinating with vehicles operated by humans. A group of autonomous and human-driven vehicles (HVs) which work together to optimize an altruistic social utility -- as opposed to the egoistic individual utility -- can co-exist seamlessly and assure safety and efficiency on the road. Achieving this mission without explicit coordination among agents is challenging, mainly due to the difficulty of predicting the behavior of humans with heterogeneous preferences in mixed-autonomy environments. Formally, we model an AV's maneuver planning in mixed-autonomy traffic as a partially-observable stochastic game and attempt to derive optimal policies that lead to socially-desirable outcomes using a multi-agent reinforcement learning framework. We introduce a quantitative representation of the AVs' social preferences and design a distributed reward structure that induces altruism into their decision making process. Our altruistic AVs are able to form alliances, guide the traffic, and affect the behavior of the HVs to handle competitive driving scenarios. As a case study, we compare egoistic AVs to our altruistic autonomous agents in a highway merging setting and demonstrate the emerging behaviors that lead to a noticeable improvement in the number of successful merges as well as the overall traffic flow and safety.

cs.RO↗

arXiv2022

Towards Learning Generalizable Driving Policies from Restricted Latent Representations

Training intelligent agents that can drive autonomously in various urban and highway scenarios has been a hot topic in the robotics society within the last decades. However, the diversity of driving environments in terms of road topology and positioning of the neighboring vehicles makes this problem very challenging. It goes without saying that although scenario-specific driving policies for autonomous driving are promising and can improve transportation safety and efficiency, they are clearly not a universal scalable solution. Instead, we seek decision-making schemes and driving policies that can generalize to novel and unseen environments. In this work, we capitalize on the key idea that human drivers learn abstract representations of their surroundings that are fairly similar among various driving scenarios and environments. Through these representations, human drivers are able to quickly adapt to novel environments and drive in unseen conditions. Formally, through imposing an information bottleneck, we extract a latent representation that minimizes the \textit{distance} -- a quantification that we introduce to gauge the similarity among different driving configurations -- between driving scenarios. This latent space is then employed as the input to a Q-learning module to learn generalizable driving policies. Our experiments revealed that, using this latent representation can reduce the number of crashes to about half.

cs.RO↗

arXiv2022

Binary Classification Under $\ell_0$ Attacks for General Noise Distribution

Adversarial examples have recently drawn considerable attention in the field of machine learning due to the fact that small perturbations in the data can result in major performance degradation. This phenomenon is usually modeled by a malicious adversary that can apply perturbations to the data in a constrained fashion, such as being bounded in a certain norm. In this paper, we study this problem when the adversary is constrained by the $\ell_0$ norm; i.e., it can perturb a certain number of coordinates in the input, but has no limit on how much it can perturb those coordinates. Due to the combinatorial nature of this setting, we need to go beyond the standard techniques in robust machine learning to address this problem. We consider a binary classification scenario where $d$ noisy data samples of the true label are provided to us after adversarial perturbations. We introduce a classification method which employs a nonlinear component called truncation, and show in an asymptotic scenario, as long as the adversary is restricted to perturb no more than $\sqrt{d}$ data samples, we can almost achieve the optimal classification error in the absence of the adversary, i.e. we can completely neutralize adversary's effect. Surprisingly, we observe a phase transition in the sense that using a converse argument, we show that if the adversary can perturb more than $\sqrt{d}$ coordinates, no classifier can do better than a random guess.

cs.LG↗

arXiv2022

Provably Private Distributed Averaging Consensus: An Information-Theoretic Approach

In this work, we focus on solving a decentralized consensus problem in a private manner. Specifically, we consider a setting in which a group of nodes, connected through a network, aim at computing the mean of their local values without revealing those values to each other. The distributed consensus problem is a classic problem that has been extensively studied and its convergence characteristics are well-known. Alas, state-of-the-art consensus methods build on the idea of exchanging local information with neighboring nodes which leaks information about the users' local values. We propose an algorithmic framework that is capable of achieving the convergence limit and rate of classic consensus algorithms while keeping the users' local values private. The key idea of our proposed method is to carefully design noisy messages that are passed from each node to its neighbors such that the consensus algorithm still converges precisely to the average of local values, while a minimum amount of information about local values is leaked. We formalize this by precisely characterizing the mutual information between the private message of a node and all the messages that another adversary collects over time. We prove that our method is capable of preserving users' privacy for any network without a so-called "generalized leaf", and formalize the trade-off between privacy and convergence time. Unlike many private algorithms, any desired accuracy is achievable by our method, and the required level of privacy only affects the convergence time.

cs.MA↗