AcL: Action Learner for Fault-Tolerant Quadruped Locomotion Control

Quadrupedal robots can learn versatile locomotion skills but remain vulnerable when one or more joints lose power. In contrast, dogs and cats can adopt limping gaits when injured, demonstrating their remarkable ability to adapt to physical conditions. Inspired by such adaptability, this paper presents Action Learner (AcL), a novel teacher-student reinforcement learning framework that enables quadrupeds to autonomously adapt their gait for stable walking under multiple joint faults. Unlike conventional teacher-student approaches that enforce strict imitation, AcL leverages teacher policies to generate style rewards, guiding the student policy without requiring precise replication. We train multiple teacher policies, each corresponding to a different fault condition, and subsequently distill them into a single student policy with an encoder-decoder architecture. While prior works primarily address single-joint faults, AcL enables quadrupeds to walk with up to four faulty joints across one or two legs, autonomously switching between different limping gaits when faults occur. We validate AcL on a real Go2 quadruped robot under single- and double-joint faults, demonstrating fault-tolerant, stable walking, smooth gait transitions between normal and lamb gaits, and robustness against external disturbances.

Symmetry constrained neural networks for detection and localization of damage in metal plates

The present paper is concerned with deep learning techniques applied to detection and localization of damage in a thin aluminum plate. We used data generated on a tabletop apparatus by mounting to the plate four piezoelectric transducers, each of which took turn to generate a Lamb wave that then traversed the region of interest before being received by the remaining three sensors. On training a neural network to analyze time-series data of the material response, which displayed damage-reflective features whenever the plate guided waves interacted with a contact load, we achieved a model that detected with greater than 99% accuracy in addition to a model that localized with $3.14 \pm 0.21$ mm mean distance error and captured more than 60% of test examples within the diffraction limit. For each task, the best-performing model was designed according to the inductive bias that our transducers were both similar and arranged in a square pattern on a nearly uniform plate.

Multistep Inverse Is Not All You Need

In real-world control settings, the observation space is often unnecessarily high-dimensional and subject to time-correlated noise. However, the controllable dynamics of the system are often far simpler than the dynamics of the raw observations. It is therefore desirable to learn an encoder to map the observation space to a simpler space of control-relevant variables. In this work, we consider the Ex-BMDP model, first proposed by Efroni et al. (2022), which formalizes control problems where observations can be factorized into an action-dependent latent state which evolves deterministically, and action-independent time-correlated noise. Lamb et al. (2022) proposes the "AC-State" method for learning an encoder to extract a complete action-dependent latent state representation from the observations in such problems. AC-State is a multistep-inverse method, in that it uses the encoding of the the first and last state in a path to predict the first action in the path. However, we identify cases where AC-State will fail to learn a correct latent representation of the agent-controllable factor of the state. We therefore propose a new algorithm, ACDF, which combines multistep-inverse prediction with a latent forward model. ACDF is guaranteed to correctly infer an action-dependent latent state encoder for a large class of Ex-BMDP models. We demonstrate the effectiveness of ACDF on tabular Ex-BMDPs through numerical simulations; as well as high-dimensional environments using neural-network-based encoders. Code is available at https://github.com/midi-lab/acdf.

23.8 GHz Acoustic Filter in Periodically Poled Piezoelectric Film Lithium Niobate with 1.52 dB IL and 19.4% FBW

This paper reports the first piezoelectric acoustic filter in periodically poled piezoelectric film (P3F) lithium niobate (LiNbO3) at 23.8 GHz with low insertion loss (IL) of 1.52 dB and 3-dB fractional bandwidth (FBW) of 19.4%. The filter features a compact footprint of 0.64 mm2. The third-order ladder filter is implemented with electrically coupled resonators in 150 nm bi-layer P3F 128 rotated Y-cut LiNbO3 thin film, operating in second-order symmetric (S2) Lamb mode. The record-breaking performance is enabled by the P3F LiNbO3 platform, where piezoelectric thin films of alternating orientations are transferred subsequently, facilitating efficient higher-order Lamb mode operation with simultaneously high quality factor (Q) and coupling coefficient (k2) at millimeter-wave (mmWave). Also, the multi-layer P3F stack promises smaller footprints and better nonlinearity than single-layer counterparts, thanks to the higher capacitance density and lower thermal resistance. Upon further development, the reported P3F LiNbO3 platform is promising for compact filters at mmWave.

Breaking MLPerf Training: A Case Study on Optimizing BERT

Speeding up the large-scale distributed training is challenging in that it requires improving various components of training including load balancing, communication, optimizers, etc. We present novel approaches for fast large-scale training of BERT model which individually ameliorates each component thereby leading to a new level of BERT training performance. Load balancing is imperative in distributed BERT training since its training datasets are characterized by samples with various lengths. Communication cost, which is proportional to the scale of distributed training, needs to be hidden by useful computation. In addition, the optimizers, e.g., ADAM, LAMB, etc., need to be carefully re-evaluated in the context of large-scale distributed training. We propose two new ideas, (1) local presorting based on dataset stratification for load balancing and (2) bucket-wise gradient clipping before allreduce which allows us to benefit from the overlap of gradient computation and synchronization as well as the fast training of gradient clipping before allreduce. We also re-evaluate existing optimizers via hyperparameter optimization and utilize ADAM, which also contributes to fast training via larger batches than existing methods. Our proposed methods, all combined, give the fastest MLPerf BERT training of 25.1 (22.3) seconds on 1,024 NVIDIA A100 GPUs, which is 1.33x (1.13x) and 1.57x faster than the other top two (one) submissions to MLPerf v1.1 (v2.0). Our implementation and evaluation results are available at MLPerf v1.1~v2.1.

Revisiting LARS for Large Batch Training Generalization of Neural Networks

LARS and LAMB have emerged as prominent techniques in Large Batch Learning (LBL), ensuring the stability of AI training. One of the primary challenges in LBL is convergence stability, where the AI agent usually gets trapped into the sharp minimizer. Addressing this challenge, a relatively recent technique, known as warm-up, has been employed. However, warm-up lacks a strong theoretical foundation, leaving the door open for further exploration of more efficacious algorithms. In light of this situation, we conduct empirical experiments to analyze the behaviors of the two most popular optimizers in the LARS family: LARS and LAMB, with and without a warm-up strategy. Our analyses give us a comprehension of the novel LARS, LAMB, and the necessity of a warm-up technique in LBL. Building upon these insights, we propose a novel algorithm called Time Varying LARS (TVLARS), which facilitates robust training in the initial phase without the need for warm-up. Experimental evaluation demonstrates that TVLARS achieves competitive results with LARS and LAMB when warm-up is utilized while surpassing their performance without the warm-up technique.

Intelligent Robotic Sonographer: Mutual Information-based Disentangled Reward Learning from Few Demonstrations

Ultrasound (US) imaging is widely used for biometric measurement and diagnosis of internal organs due to the advantages of being real-time and radiation-free. However, due to high inter-operator variability, resulting images highly depend on operators' experience. In this work, an intelligent robotic sonographer is proposed to autonomously "explore" target anatomies and navigate a US probe to a relevant 2D plane by learning from expert. The underlying high-level physiological knowledge from experts is inferred by a neural reward function, using a ranked pairwise image comparisons approach in a self-supervised fashion. This process can be referred to as understanding the "language of sonography". Considering the generalization capability to overcome inter-patient variations, mutual information is estimated by a network to explicitly extract the task-related and domain features in latent space. Besides, a Gaussian distribution-based filter is developed to automatically evaluate and take the quality of the expert's demonstrations into account. The robotic localization is carried out in coarse-to-fine mode based on the predicted reward associated to B-mode images. To demonstrate the performance of the proposed approach, representative experiments for the "line" target and "point" target are performed on vascular phantom and two ex-vivo animal organ phantoms (chicken heart and lamb kidney), respectively. The results demonstrated that the proposed advanced framework can robustly work on different kinds of known and unseen phantoms.

CAME: Confidence-guided Adaptive Memory Efficient Optimization

Adaptive gradient methods, such as Adam and LAMB, have demonstrated excellent performance in the training of large language models. Nevertheless, the need for adaptivity requires maintaining second-moment estimates of the per-parameter gradients, which entails a high cost of extra memory overheads. To solve this problem, several memory-efficient optimizers (e.g., Adafactor) have been proposed to obtain a drastic reduction in auxiliary memory usage, but with a performance penalty. In this paper, we first study a confidence-guided strategy to reduce the instability of existing memory efficient optimizers. Based on this strategy, we propose CAME to simultaneously achieve two goals: fast convergence as in traditional adaptive methods, and low memory usage as in memory-efficient methods. Extensive experiments demonstrate the training stability and superior performance of CAME across various NLP tasks such as BERT and GPT-2 training. Notably, for BERT pre-training on the large batch size of 32,768, our proposed optimizer attains faster convergence and higher accuracy compared with the Adam optimizer. The implementation of CAME is publicly available.

MKOR: Momentum-Enabled Kronecker-Factor-Based Optimizer Using Rank-1 Updates

This work proposes a Momentum-Enabled Kronecker-Factor-Based Optimizer Using Rank-1 updates, called MKOR, that improves the training time and convergence properties of deep neural networks (DNNs). Second-order techniques, while enjoying higher convergence rates vs first-order counterparts, have cubic complexity with respect to either the model size and/or the training batch size. Hence they exhibit poor scalability and performance in transformer models, e.g. large language models (LLMs), because the batch sizes in these models scale by the attention mechanism sequence length, leading to large model size and batch sizes. MKOR's complexity is quadratic with respect to the model size, alleviating the computation bottlenecks in second-order methods. Because of their high computation complexity, state-of-the-art implementations of second-order methods can only afford to update the second order information infrequently, and thus do not fully exploit the promise of better convergence from these updates. By reducing the communication complexity of the second-order updates as well as achieving a linear communication complexity, MKOR increases the frequency of second order updates. We also propose a hybrid version of MKOR (called MKOR-H) that mid-training falls backs to a first order optimizer if the second order updates no longer accelerate convergence. Our experiments show that MKOR outperforms state -of-the-art first order methods, e.g. the LAMB optimizer, and best implementations of second-order methods, i.e. KAISA/KFAC, up to 2.57x and 1.85x respectively on BERT-Large-Uncased on 64 GPUs.

Limitations of curl and directional filters in elastography

In the approaches to elastography, two mathematical operations have been frequently applied to improve the final estimate of shear wave speed and shear modulus of tissues. The vector curl operator can separate out the transverse component of a complicated displacement field, and directional filters can separate distinct orientations of wave propagation. However, there are practical limitations that can prevent the intended improvement in elastography estimates. Some simple configurations of wavefields relevant to elastography are examined against theoretical models within the semi-infinite elastic medium and guided waves in a bounded medium. The Miller-Pursey solutions in simplified form are examined for the semi-infinite medium and the Lamb wave symmetric form is considered for the guided wave structure. In both cases, wave combinations along with practical limits on the imaging plane can prevent the curl and directional filter operations from directly providing an improved measure of shear wave speed and shear modulus. Additional limits on signal-to-noise and the support of filters also restrict the applica-bility of these strategies for improving elastographic measures. Practical implementations of shear wave excitations applied to the body and to bounded structures within the body can involve waves that are not easily resolved by the vector curl operator and directional filters. These limits may be overcome by more advanced strategies or simple improvements in baseline parameters including the size of the region of interest and the number of shear waves propagated within.