PRPeter J. Ramadge

Peter J. Ramadge

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Peter J. Ramadge has a total of 51 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Dissecting Transformer Length Extrapolation via the Lens of Receptive Field Analysis

    by Ta-Chung Chi, Ting-Han Fan, Alexander I. Rudnicky, Peter J. Ramadge

    Length extrapolation permits training a transformer language model on short sequences that preserves perplexities when tested on substantially longer sequences. A relative positional embedding design, ALiBi, has had the widest usage to date. We dissect ALiBi via the lens of receptive field analysis empowered by a novel cumulative normalized gradient tool. The concept of receptive field further allows us to modify the vanilla Sinusoidal positional embedding to create ~\textbf{Sandwich}, the first parameter-free relative positional embedding design that truly length information uses longer than the training sequence. Sandwich shares with KERPLE and T5 the same logarithmic decaying temporal bias pattern with learnable relative positional embeddings; these elucidate future extrapolatable positional embedding design.

  • Open Access

    Transformer Working Memory Enables Regular Language Reasoning and Natural Language Length Extrapolation

    by Ta-Chung Chi, Ting-Han Fan, Alexander I. Rudnicky, Peter J. Ramadge

    Unlike recurrent models, conventional wisdom has it that Transformers cannot perfectly model regular languages. Inspired by the notion of working memory, we propose a new Transformer variant named RegularGPT. With its novel combination of Weight-Sharing, Adaptive-Depth, and Sliding-Dilated-Attention, RegularGPT constructs working memory along the depth dimension, thereby enabling efficient and successful modeling of regular languages such as PARITY. We further test RegularGPT on the task of natural language length extrapolation and surprisingly find that it rediscovers the local windowed attention effect deemed necessary in prior work for length extrapolation.

  • Open Access

    Transformer Working Memory Enables Regular Language Reasoning And Natural Language Length Extrapolation

    by Ta-Chung Chi, Ting-Han Fan, Alexander Rudnicky, Peter Ramadge

    Ta-Chung Chi, Ting-Han Fan, Alexander Rudnicky, Peter Ramadge. Findings of the Association for Computational Linguistics: EMNLP 2023. 2023.


  • Top Cited Papers
    Open Access

    Latent Positional Information is in the Self-Attention Variance of Transformer Language Models Without Positional Embeddings

    by Ta-Chung Chi, Ting-Han Fan, Li-Wei Chen, Alexander Rudnicky, Peter Ramadge

    Ta-Chung Chi, Ting-Han Fan, Li-Wei Chen, Alexander Rudnicky, Peter Ramadge. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 2023.


  • Open Access

    KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation

    by Ta-Chung Chi, Ting-Han Fan, Peter J. Ramadge, Alexander I. Rudnicky

    Relative positional embeddings (RPE) have received considerable attention since RPEs effectively model the relative distance among tokens and enable length extrapolation. We propose KERPLE, a framework that generalizes relative position embedding for extrapolation by kernelizing positional differences. We achieve this goal using conditionally positive definite (CPD) kernels, a class of functions known for generalizing distance metrics. To maintain the inner product interpretation of self-attention, we show that a CPD kernel can be transformed into a PD kernel by adding a constant offset. This offset is implicitly absorbed in the Softmax normalization during self-attention. The diversity of CPD kernels allows us to derive various RPEs that enable length extrapolation in a principled way. Experiments demonstrate that the logarithmic variant achieves excellent extrapolation performance on three large language modeling datasets. Our implementation and pretrained checkpoints are released at https://github.com/chijames/KERPLE.git.

  • Open Access

    DiffLoop: Tuning PID controllers by differentiating through the feedback loop

    by Athindran Ramesh Kumar, Peter J. Ramadge

    Since most industrial control applications use PID controllers, PID tuning and anti-windup measures are significant problems. This paper investigates tuning the feedback gains of a PID controller via back-calculation and automatic differentiation tools. In particular, we episodically use a cost function to generate gradients and perform gradient descent to improve controller performance. We provide a theoretical framework for analyzing this non-convex optimization and establish a relationship between back-calculation and disturbance feedback policies. We include numerical experiments on linear systems with actuator saturation to show the efficacy of this approach.

  • Open Access

    ProBF: Learning Probabilistic Safety Certificates with Barrier Functions

    by Athindran Ramesh Kumar, Sulin Liu, Jaime F. Fisac, Ryan P. Adams, Peter J. Ramadge

    Safety-critical applications require controllers/policies that can guarantee safety with high confidence. The control barrier function is a useful tool to guarantee safety if we have access to the ground-truth system dynamics. In practice, we have inaccurate knowledge of the system dynamics, which can lead to unsafe behaviors due to unmodeled residual dynamics. Learning the residual dynamics with deterministic machine learning models can prevent the unsafe behavior but can fail when the predictions are imperfect. In this situation, a probabilistic learning method that reasons about the uncertainty of its predictions can help provide robust safety margins. In this work, we use a Gaussian process to model the projection of the residual dynamics onto a control barrier function. We propose a novel optimization procedure to generate safe controls that can guarantee safety with high probability. The safety filter is provided with the ability to reason about the uncertainty of the predictions from the GP. We show the efficacy of this method through experiments on Segway and Quadrotor simulations. Our proposed probabilistic approach is able to reduce the number of safety violations significantly as compared to the deterministic approach with a neural network.

  • Expert Intervention Learning

    by Jonathan Spencer, Sanjiban Choudhury, Matthew Barnes, Matthew Schmittle, Mung Chiang, Peter Ramadge, Sidd Srinivasa


  • Open Access

    Safe Reinforcement Learning with Natural Language Constraints

    by Tsung-Yen Yang, Michael Hu, Yinlam Chow, Peter J. Ramadge, Karthik Narasimhan

    While safe reinforcement learning (RL) holds great promise for many practical applications like robotics or autonomous cars, current approaches require specifying constraints in mathematical form. Such specifications demand domain expertise, limiting the adoption of safe RL. In this paper, we propose learning to interpret natural language constraints for safe RL. To this end, we first introduce HazardWorld, a new multi-task benchmark that requires an agent to optimize reward while not violating constraints specified in free-form text. We then develop an agent with a modular architecture that can interpret and adhere to such textual constraints while learning new tasks. Our model consists of (1) a constraint interpreter that encodes textual constraints into spatial and temporal representations of forbidden states, and (2) a policy network that uses these representations to produce a policy achieving minimal constraint violations during training. Across different domains in HazardWorld, we show that our method achieves higher rewards (up to11x) and fewer constraint violations (by 1.8x) compared to existing approaches. However, in terms of absolute performance, HazardWorld still poses significant challenges for agents to learn efficiently, motivating the need for future work.

  • An Experimental Study of Balance in Matrix Factorization

    by Jennifer Hsia, Peter J. Ramadge

    We experimentally examine how gradient descent navigates the landscape of matrix factorization to obtain a global minimum. First, we review the critical points of matrix factorization and introduce a balanced factorization. By focusing on the balanced critical point at the origin and a subspace of unbalanced critical points, we study the effect of balance on gradient descent, including an initially unbalanced factorization and adding a balance-regularizer to the objective in the MF problem. Simulations demonstrate that maintaining a balanced factorization enables faster escape from saddle points and overall faster convergence to a global minimum.