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.
MixDiff detects OOD samples in constrained access environments by comparing perturbed samples.
Opportunistic spectrum access is one of the emerging techniques for maximizing throughput in congested bands and is enabled by predicting idle slots in spectrum. We propose a kernel-based reinforcement learning approach coupled with a novel budget-constrained sparsification technique that efficiently captures the envir…
Offline RL tackles resource-constrained online deployment with improved policy transfer.
New adaptive methods for constrained convex optimization and variational inequalities.
New sampling methods for constrained and composite distributions.
Paper uses RL to solve constrained combinatorial optimization problems.
PoET-BiN reduces power consumption in neural networks on embedded devices.
Novel evolutionary strategy solves stochastic constrained optimization problems.
Paper proposes a shape-constrained approach to distributionally robust learning.
A new algorithm for solving constrained convex optimization problems efficiently.
Oracle-efficient algorithm for offline RL with partial data coverage.
Improved Frank-Wolfe algorithm for constrained convex optimization with nearest extreme point oracle.
Houdini finds high-dimensional saddle points under few constraints.
Develops an online method for solving constrained optimization problems with debiasing techniques.
Study creates open-access wildfire dataset for Russia.
Foot-mounted inertial positioning (FMIP) can face problems of inertial drifts and unknown initial states in real applications, which renders the estimated trajectories inaccurate and not obtained in a well defined coordinate system for matching trajectories of different users. In this paper, an approach adopting receiv…
This paper examines the dividend and investment policies of a cash constrained firm that has access to costly external funding. We depart from the literature by allowing the firm to issue collateralized debt to increase its investment in productive assets resulting in a performance sensitive interest rate on debt. We f…
A recent strategy to circumvent the exploding and vanishing gradient problem in RNNs, and to allow the stable propagation of signals over long time scales, is to constrain recurrent connectivity matrices to be orthogonal or unitary. This ensures eigenvalues with unit norm and thus stable dynamics and training. However …
We introduce a DNN training technique that learns only a fraction of the full parameter set without incurring an accuracy penalty. To do this, our algorithm constrains the total number of weights updated during backpropagation to those with the highest total gradients. The remaining weights are not tracked, and their i…
ModHiFi identifies critical components for model modification without gradients or loss function.
We extend the Frank-Wolfe (FW) optimization algorithm to solve constrained smooth convex-concave saddle point (SP) problems. Remarkably, the method only requires access to linear minimization oracles. Leveraging recent advances in FW optimization, we provide the first proof of convergence of a FW-type saddle point solv…
Unified R packages for forecast reconciliation of constrained series.
Develops methods to measure and reduce fairness in datasets with limited protected attribute labels.
New algorithm reduces sample complexity for safe reinforcement learning.
Paper uses Gaussian processes to solve AC-OPF with renewable uncertainty.
Detects drifts in data for classification tasks using constrained embeddings.
New algorithm solves constrained MDPs with generative model, reducing sample complexity.
We consider the problem of improving fairness when one lacks access to a dataset labeled with protected groups, making it difficult to take advantage of strategies that can improve fairness but require protected group labels, either at training or runtime. To address this, we investigate improving fairness metrics for …
We show that a critical vulnerability in adversarial imitation is the tendency of discriminator networks to learn spurious associations between visual features and expert labels. When the discriminator focuses on task-irrelevant features, it does not provide an informative reward signal, leading to poor task performanc…
A bandit algorithm reduces regret in noisy, communication-constrained feedback.
New bounds for learning near-optimal policies in CMDPs with constraints.
New framework bridges climate science and ML for easier climate model emulation.
Meta-learning improves drone trajectory design for dynamic wireless networks.
Adversarial attacks have exposed a significant security vulnerability in state-of-the-art machine learning models. Among these models include deep reinforcement learning agents. The existing methods for attacking reinforcement learning agents assume the adversary either has access to the target agent's learned paramete…
A lot of effort has been invested into characterizing the convergence rates of gradient based algorithms for non-linear convex optimization. Recently, motivated by large datasets and problems in machine learning, the interest has shifted towards distributed optimization. In this work we present a distributed algorithm …
In this paper, we present a new approach to learning cascaded classifiers for use in computing environments that involve networks of heterogeneous and resource-constrained, low-power embedded compute and sensing nodes. We present a generalization of the classical linear detection cascade to the case of tree-structured …
PDO optimizes LLM prompts without labels, improving performance.
We introduce a novel scheme to train binary convolutional neural networks (CNNs) -- CNNs with weights and activations constrained to {-1,+1} at run-time. It has been known that using binary weights and activations drastically reduce memory size and accesses, and can replace arithmetic operations with more efficient bit…
SmartDeal reduces energy and storage costs for deep neural networks.
Improved algorithms for convex-concave min-max optimization and monotone variational inequalities.
We consider variational inequalities coming from monotone operators, a setting that includes convex minimization and convex-concave saddle-point problems. We assume an access to potentially noisy unbiased values of the monotone operators and assess convergence through a compatible gap function which corresponds to the …
Performance analysis, from the external point of view of a client who would only have access to returns and holdings of a fund, evolved towards exact attribution made in the context of portfolio optimisation, which is the internal point of view of a manager controlling all the parameters of this optimisation. Attributi…
In this paper, we study the problem of constrained robust (min-max) optimization ina black-box setting, where the desired optimizer cannot access the gradients of the objective function but may query its values. We present a principled optimization framework, integrating a zeroth-order (ZO) gradient estimator with an a…
New method optimizes submanifolds without explicit manifold details.
Despite remarkable advances in automated visual recognition by machines, some visual tasks remain challenging for machines. Fleuret et al. (2011) introduced the Synthetic Visual Reasoning Test (SVRT) to highlight this point, which required classification of images consisting of randomly generated shapes based on hidden…
This paper presents a physics-based data-driven method to learn predictive reduced-order models (ROMs) from high-fidelity simulations, and illustrates it in the challenging context of a single-injector combustion process. The method combines the perspectives of model reduction and machine learning. Model reduction brin…
Consider a social network where only a few nodes (agents) have meaningful interactions in the sense that the conditional dependency graph over node attribute variables (behaviors) is sparse. A company that can only observe the interactions between its own customers will generally not be able to accurately estimate its …
While the backpropagation of error algorithm enables deep neural network training, it implies (i) bidirectional synaptic weight transport and (ii) update locking until the forward and backward passes are completed. Not only do these constraints preclude biological plausibility, but they also hinder the development of l…