_id,title
9571,NUQSGD: Provably communication-efficient data-parallel SGD via nonuniform quantization
9620,Collecting coupons is faster with friends
9543,New bounds for distributed mean estimation and variance reduction
9823,"Wait-free approximate agreement onÂ graphs"
8723,Breaking (global) barriers in parallel stochastic optimization with wait-avoiding group averaging
9951,Comparison dynamics in population protocols
8191,Memory tagging: Minimalist synchronization for scalable concurrent data structures
8268,Compressive sensing using iterative hard thresholding with low precision data representation: Theory and applications
8286,Dynamic averaging load balancing on cycles
8383,Brief Announcement: Why Extension-Based Proofs Fail
8722,Taming unbalanced training workloads in deep learning with partial collective operations
7605,In search of the fastest concurrent union-find algorithm
7635,Testing concurrency on the JVM with Lincheck
7636,Non-blocking interpolation search trees with doubly-logarithmic running time
8725,The splay-list: A distribution-adaptive concurrent skip-list
8724,On the sample complexity of adversarial multi-source PAC learning
9415,Inducing and exploiting activation sparsity for fast neural network inference
9632,WoodFisher: Efficient second-order approximation for neural network compression
9631,Scalable belief propagation via relaxed scheduling
7201,SparCML: High-performance sparse communication for machine learning
7228,Scalable FIFO channels for programming via communicating sequential processes
7437,Distributed learning over unreliable networks
7542,Powerset convolutional neural networks
6485,Lock-free channels for programming via communicating sequential processes
6673,Efficiency guarantees for parallel incremental algorithms under relaxed schedulers
6676,Why extension-based proofs fail
7122,Gradient compression for communication-limited convex optimization
7812,Model compression via distillation and quantization
536,Communication-efficient randomized consensus
5961,A brief tutorial on distributed and concurrent machine learning
5962,The convergence of stochastic gradient descent in asynchronous shared memory
5963,Relaxed schedulers can efficiently parallelize iterative algorithms
5964,Brief Announcement: Performance prediction for coarse-grained locking
5965,Distributionally linearizable data structures
5966,The transactional conflict problem
6001,ThreadScan: Automatic and scalable memory reclamation
6031,Fast quantized arithmetic on x86: Trading compute for data movement
6558,Byzantine Stochastic Gradient Descent
6589,The convergence of sparsified gradient methods
7116,Synchronous multi-GPU training for deep learning with low-precision communications: An empirical study
7123,Space-optimal majority in population protocols
787,Time-space trade-offs in population protocols
788,Robust detection in leak-prone population protocols
789,Forkscan: Conservative memory reclamation for modern operating systems
790,FPGA-accelerated dense linear machine learning: A precision-convergence trade-off
791,The power of choice in priority scheduling
487,Towards unlicensed cellular networks in TV white spaces
431,QSGD: Communication-efficient SGD via gradient quantization and encoding
432,"ZipML: Training linear models with end-to-end low precision, and a little bit of deep learning"
785,Lease/Release: Architectural support for scaling contended data structures
786,Are lock free concurrent algorithms practically wait free
776,The SprayList: A scalable relaxed priority queue
777,Streaming min-max hypergraph partitioning
778,Inherent limitations of hybrid transactional memory
779,ThreadScan: Automatic and scalable memory reclamation
780,Polylogarithmic-time leader election in population protocols
781,Fast and exact majority in population protocols
782,Lock-Free algorithms under stochastic schedulers
783,How to elect a leader faster than a tournament
784,"A high-radix, low-latency optical switch for data centers"
768,Dynamic task allocation in asynchronous shared memory
769,Tight bounds for asynchronous renaming
770,StackTrack: An automated transactional approach to concurrent memory reclamation
771,Balls-into-Leaves: Sub-logarithmic renaming in synchronous message-passing systems
772,Are lock-free concurrent algorithms practically wait-free?
773,Communication-efficient randomized consensus
774,Brief announcement: Are lock-free concurrent algorithms practically wait-free?
775,"The levelarray: A fast, practical long-lived renaming algorithm"
765,Randomized loose renaming in O(loglogn) time
762,On the cost of composing shared-memory algorithms
763,Early deciding synchronous renaming in O(log f) rounds or less
764,"Of choices, failures and asynchrony: the many faces of set agreement"
766,How to allocate tasks asynchronously
767,Generating Fast Indulgent Algorithms
757,Generating fast indulgent algorithms
759,The complexity of renaming
760,Sub-logarithmic test-and-set against a weak adversary
761,"Optimal-time adaptive strong renaming, with applications to counting"
754,Fast randomized test-and-set and renaming
755,How efficient can gossip be? (On the cost of resilient information exchange)
756,Securing every bit: Authenticated broadcast in radio networks
758,Brief announcement: New bounds for partially synchronous set agreement
752,"Of choices, failures and asynchrony: the many faces of set agreement"
753,How to solve consensus in the smallest window of synchrony