Related papers: Confidence-gated training for efficient early-exit…
Reinforcement learning with verifiable rewards (RLVR) typically optimizes for outcome rewards without imposing constraints on intermediate reasoning. This leaves training susceptible to reward hacking, where models exploit loopholes (e.g.,…
We introduce Perturbative Gradient Training (PGT), a novel training paradigm that overcomes a critical limitation of physical reservoir computing: the inability to perform backpropagation due to the black-box nature of physical reservoirs.…
The remarkable performance gains realized by large pretrained models, e.g., GPT-3, hinge on the massive amounts of data they are exposed to during training. Analogously, distilling such large models to compact models for efficient…
For many practical applications, a high computational cost of inference over deep network architectures might be unacceptable. A small degradation in the overall inference accuracy might be a reasonable price to pay for a significant…
Deep neural network models owe their representational power to the high number of learnable parameters. It is often infeasible to run these largely parametrized deep models in limited resource environments, like mobile phones. Network…
As Internet of Things (IoT) technology advances, end devices like sensors and smartphones are progressively equipped with AI models tailored to their local memory and computational constraints. Local inference reduces communication costs…
Recently, a growing body of research has focused on either optimizing CTR model architectures to better model feature interactions or refining training objectives to aid parameter learning, thereby achieving better predictive performance.…
We study a systems-level visual inference problem: using an expensive privileged modality during training while preserving a fixed-cost, single-modality deployment path. We present JDCNet, a confidence-gated CT-to-X-ray distillation…
Early exits enable the network's forward pass to terminate early by attaching trainable internal classifiers to the backbone network. Existing early-exit methods typically adopt either a joint training approach, where the backbone and exit…
Conditional entropy models effectively leverage spatio-temporal contexts to reduce video redundancy. However, incorporating temporal context often introduces additional model complexity and increases computational cost. In parallel, many…
Modern predictive models are often deployed to environments in which computational budgets are dynamic. Anytime algorithms are well-suited to such environments as, at any point during computation, they can output a prediction whose quality…
In this paper, we present CT-AGD (Curvature-Tuned Accelerated Gradient Descent), an optimization method for non-convex optimization problems in deep learning training tasks. CT-AGD is a general boosting procedure that accelerates…
The concept of conditional computation for deep nets has been proposed previously to improve model performance by selectively using only parts of the model conditioned on the sample it is processing. In this paper, we investigate…
Gradient regularization (GR) is a method that penalizes the gradient norm of the training loss during training. While some studies have reported that GR can improve generalization performance, little attention has been paid to it from the…
Forward Gradients - the idea of using directional derivatives in forward differentiation mode - have recently been shown to be utilizable for neural network training while avoiding problems generally associated with backpropagation gradient…
Training deep neural network classifiers that are certifiably robust against adversarial attacks is critical to ensuring the security and reliability of AI-controlled systems. Although numerous state-of-the-art certified training methods…
Gating mechanisms are widely used in neural network models, where they allow gradients to backpropagate more easily through depth or time. However, their saturation property introduces problems of its own. For example, in recurrent models…
As advances in Deep Neural Networks (DNNs) demonstrate unprecedented levels of performance in many critical applications, their vulnerability to attacks is still an open question. We consider evasion attacks at testing time against Deep…
Saliency methods have been widely used to highlight important input features in model predictions. Most existing methods use backpropagation on a modified gradient function to generate saliency maps. Thus, noisy gradients can result in…
Scaling machine learning models significantly improves their performance. However, such gains come at the cost of inference being slow and resource-intensive. Early-exit neural networks (EENNs) offer a promising solution: they accelerate…