Search for: All records

Recursion is the fundamental paradigm to finitely describe potentially infinite objects. As state-of-the-art reinforcement learning (RL) algorithms cannot directly reason about recursion, they must rely on the practitioner's ingenuity in designing a suitable "flat" representation of the environment. The resulting manual feature constructions and approximations are cumbersome and error-prone; their lack of transparency hampers scalability. To overcome these challenges, we develop RL algorithms capable of computing optimal policies in environments described as a collection of Markov decision processes (MDPs) that can recursively invoke one another. Each constituent MDP is characterized by several entry and exit points that correspond to input and output values of these invocations. These recursive MDPs (or RMDPs) are expressively equivalent to probabilistic pushdown systems (with call-stack playing the role of the pushdown stack), and can model probabilistic programs with recursive procedural calls. We introduce Recursive Q-learning---a model-free RL algorithm for RMDPs---and prove that it converges for finite, single-exit and deterministic multi-exit RMDPs under mild assumptions. 

While neural network binary classifiers are often evaluated on metrics such as Accuracy and F1-Score, they are commonly trained with a cross-entropy objective. How can this training-evaluation gap be addressed? While specific techniques have been adopted to optimize certain confusion matrix based metrics, it is challenging or impossible in some cases to generalize the techniques to other metrics. Adversarial learning approaches have also been proposed to optimize networks via confusion matrix based metrics, but they tend to be much slower than common training methods. In this work, we propose a unifying approach to training neural network binary classifiers that combines a differentiable approximation of the Heaviside function with a probabilistic view of the typical confusion matrix values using soft sets. Our theoretical analysis shows the benefit of using our method to optimize for a given evaluation metric, such as F1-Score, with soft sets, and our extensive experiments show the effectiveness of our approach in several domains. 

Fairness has become an important topic in machine learning. Generally, most literature on fairness assumes that the sensitive information, such as gender or race, is present in the training set, and uses this information to mitigate bias. However, due to practical concerns like privacy and regulation, applications of these methods are restricted. Also, although much of the literature studies supervised learning, in many real-world scenarios, we want to utilize the large unlabelled dataset to improve the model's accuracy. Can we improve fair classification without sensitive information and without labels? To tackle the problem, in this paper, we propose a novel reweighing-based contrastive learning method. The goal of our method is to learn a generally fair representation without observing sensitive attributes.Our method assigns weights to training samples per iteration based on their gradient directions relative to the validation samples such that the average top-k validation loss is minimized. Compared with past fairness methods without demographics, our method is built on fully unsupervised training data and requires only a small labelled validation set. We provide rigorous theoretical proof of the convergence of our model. Experimental results show that our proposed method achieves better or comparable performance than state-of-the-art methods on three datasets in terms of accuracy and several fairness metrics. 

Most of existing work on fairness assumes available demographic information in the training set. In practice, due to legal or privacy concerns, when demographic information is not available in the training set, it is crucial to find alternative objectives to ensure fairness. Existing work on fairness without demographics follows Rawlsian Max-Min fairness objectives. However, such constraints could be too strict to improve group fairness, and could lead to a great decrease in accuracy. In light of these limitations, in this paper, we propose to solve the problem from a new perspective, i.e., through knowledge distillation. Our method uses soft label from an overfitted teacher model as an alternative, and we show from preliminary experiments that soft labelling is beneficial for improving fairness. We analyze theoretically the fairness of our method, and we show that our method can be treated as an error-based reweighing. Experimental results on three datasets show that our method outperforms state-of-the-art alternatives, with notable improvements in group fairness and with relatively small decrease in accuracy. 

While much progress has been made in understanding the minimax sample complexity of reinforcement learning (RL)—the complexity of learning on the “worst-case” instance—such measures of complexity often do not capture the true difficulty of learning. In practice, on an “easy” instance, we might hope to achieve a complexity far better than that achievable on the worst-case instance. In this work we seek to understand the “instance-dependent” complexity of learning near-optimal policies (PAC RL) in the setting of RL with linear function approximation. We propose an algorithm, Pedel, which achieves a fine-grained instance-dependent measure of complexity, the first of its kind in the RL with function approximation setting, thereby capturing the difficulty of learning on each particular problem instance. Through an explicit example, we show that Pedel yields provable gains over low-regret, minimax-optimal algorithms and that such algorithms are unable to hit the instance-optimal rate. Our approach relies on a novel online experiment design-based procedure which focuses the exploration budget on the “directions” most relevant to learning a near-optimal policy, and may be of independent interest. 

This paper targets at improving the generalizability of hypergraph neural networks in the low-label regime, through applying the contrastive learning approach from images/graphs (we refer to it as HyperGCL). We focus on the following question: How to construct contrastive views for hypergraphs via augmentations? We provide the solutions in two folds. First, guided by domain knowledge, we fabricate two schemes to augment hyperedges with higher-order relations encoded, and adopt three vertex augmentation strategies from graph-structured data. Second, in search of more effective views in a data-driven manner, we for the first time propose a hypergraph generative model to generate augmented views, and then an end-to-end differentiable pipeline to jointly learn hypergraph augmentations and model parameters. Our technical innovations are reflected in designing both fabricated and generative augmentations of hypergraphs. The experimental findings include: (i) Among fabricated augmentations in HyperGCL, augmenting hyperedges provides the most numerical gains, implying that higher-order information in structures is usually more downstream-relevant; (ii) Generative augmentations do better in preserving higher-order information to further benefit generalizability; (iii) HyperGCL also boosts robustness and fairness in hypergraph representation learning. Codes are released at https://github.com/weitianxin/HyperGCL. 

In the stochastic contextual bandit setting, regret-minimizing algorithms have been extensively researched, but their instance-minimizing best-arm identification counterparts remain seldom studied. In this work, we focus on the stochastic bandit problem in the (ǫ, δ)-PAC setting: given a policy class Π the goal of the learner is to return a policy π ∈ Π whose expected reward is within ǫ of the optimal policy with probability greater than 1 − δ. We characterize the first instance-dependent PAC sample complexity of contextual bandits through a quantity ρΠ, and provide matching upper and lower bounds in terms of ρΠ for the agnostic and linear contextual best-arm identification settings. We show that no algorithm can be simultaneously minimax-optimal for regret minimization and instance-dependent PAC for best-arm identification. Our main result is a new instance-optimal and computationally efficient algorithm that relies on a polynomial number of calls to an argmax oracle. 

Machine Learning (ML) research has focused on maximizing the accuracy of predictive tasks. ML models, however, are increasingly more complex, resource intensive, and costlier to deploy in resource-constrained environments. These issues are exacerbated for prediction tasks with sequential classification on progressively transitioned stages with “happens-before” relation between them.We argue that it is possible to “unfold” a monolithic single multi-class classifier, typically trained for all stages using all data, into a series of single-stage classifiers. Each single- stage classifier can be cascaded gradually from cheaper to more expensive binary classifiers that are trained using only the necessary data modalities or features required for that stage. UnfoldML is a cost-aware and uncertainty-based dynamic 2D prediction pipeline for multi-stage classification that enables (1) navigation of the accuracy/cost tradeoff space, (2) reducing the spatio-temporal cost of inference by orders of magnitude, and (3) early prediction on proceeding stages. UnfoldML achieves orders of magnitude better cost in clinical settings, while detecting multi- stage disease development in real time. It achieves within 0.1% accuracy from the highest-performing multi-class baseline, while saving close to 20X on spatio- temporal cost of inference and earlier (3.5hrs) disease onset prediction. We also show that UnfoldML generalizes to image classification, where it can predict different level of labels (from coarse to fine) given different level of abstractions of a image, saving close to 5X cost with as little as 0.4% accuracy reduction. 

The quantum many-body problem lies at the center of the most important open challenges in condensed matter, quantum chemistry, atomic, nuclear, and high-energy physics. While quantum Monte Carlo, when applicable, remains the most powerful numerical technique capable of treating dozens or hundreds of degrees of freedom with high accuracy, it is restricted to models that are not afflicted by the infamous sign problem. A powerful alternative that has emerged in recent years is the use of neural networks as variational estimators for quantum states. In this work, we propose a symmetry-projected variational solution in the form of linear combinations of simple restricted Boltzmann machines. This construction allows one to explore states outside of the original variational manifold and increase the representation power with moderate computational effort. Besides allowing one to restore spatial symmetries, an expansion in terms of Krylov states using a Lanczos recursion offers a solution that can further improve the quantum state accuracy. We illustrate these ideas with an application to the Heisenberg J1−J2 model on the square lattice, a paradigmatic problem under debate in condensed matter physics, and achieve state-of-the-art accuracy in the representation of the ground state.